© 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. 108527
    Prev
    Next
    INDEX
    Explanations

    own

    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
    å¾Īå¤ļæľĭåıĭ
    -0.29
    ilion
    -0.29
    builders
    -0.28
    å°ıæŶåīį
    -0.28
    anmar
    -0.27
     fellows
    -0.27
     Celt
    -0.27
    æĸ°æīĭ
    -0.26
     foes
    -0.25
    åѦçĶŁä»¬
    -0.25
    POSITIVE LOGITS
     your
    0.36
    èĩªå·±çļĦ
    0.35
    own
    0.34
     own
    0.33
     current
    0.33
     Your
    0.31
     YOUR
    0.31
    èĩªèº«çļĦ
    0.30
     primary
    0.30
    ogh
    0.30
    Activations Density 1.040%

    No Known Activations