© 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. 108856
    Prev
    Next
    INDEX
    Explanations

    the

    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
     plc
    -0.28
    apult
    -0.27
     civilized
    -0.27
    gé
    -0.27
    å°±æĺ¯åĽłä¸º
    -0.26
    thumbs
    -0.26
    -members
    -0.26
    -basket
    -0.26
    ìn
    -0.26
    ç®ĹäºĨ
    -0.25
    POSITIVE LOGITS
     Mag
    0.29
     Ord
    0.28
     WH
    0.28
    笺
    0.28
     given
    0.28
     Wh
    0.28
    Mag
    0.28
     Tr
    0.28
    tc
    0.27
    æīĺ
    0.26
    Activations Density 1.068%

    No Known Activations