© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 108037
    Prev
    Next
    INDEX
    Explanations

    scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¹ĭåīįçļĦ
    -0.36
    éĤ£æł·
    -0.34
    æĹ¶ä»£çļĦ
    -0.28
    éĤ£æł·çļĦ
    -0.28
     previous
    -0.26
    //---------------------------------------------------------------------------↵↵
    -0.26
    */)↵
    -0.26
    kul
    -0.25
    .COMP
    -0.25
    vent
    -0.25
    POSITIVE LOGITS
    çİĩè¾¾
    0.28
     puff
    0.25
     mike
    0.24
     Bills
    0.24
     Uph
    0.24
    ;br
    0.24
     Bags
    0.24
    ccb
    0.23
    饲
    0.23
    :model
    0.23
    Activations Density 0.917%

    No Known Activations