© 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. 12-TRANSCODER-HP
    7. 22814
    Prev
    Next
    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vary
    -0.29
    bers
    -0.28
    é³į
    -0.27
     curing
    -0.26
    true
    -0.26
    ëĤ¸
    -0.26
    ä¼į
    -0.26
    zy
    -0.24
     vera
    -0.24
    hs
    -0.23
    POSITIVE LOGITS
    éĤ£ä»½
    0.31
    ftype
    0.29
    ä¾ĭè¡Į
    0.28
    ç¾¹
    0.28
    å¥ĸ项
    0.28
    fdc
    0.28
    软
    0.27
     divis
    0.26
     divisor
    0.26
    upa
    0.25
    Activations Density 0.000%

    No Known Activations