© 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. 22811
    Prev
    Next
    INDEX
    Explanations

    know

    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
    LOT
    -0.27
    olum
    -0.26
    itional
    -0.25
     oxidation
    -0.25
    \Template
    -0.25
    ä¸Ńæ¯Ĵ
    -0.24
    onders
    -0.23
    lots
    -0.23
    poser
    -0.23
    ä¸ĢæľŁ
    -0.23
    POSITIVE LOGITS
    让åѦçĶŁ
    0.28
    ÑģÑĤÑĢел
    0.26
     tame
    0.26
    ,var
    0.25
    å¿į
    0.24
    åŁ¹åħ»åѦçĶŁ
    0.24
    åѦçĶŁ
    0.24
    odate
    0.24
    _criteria
    0.23
     lorem
    0.23
    Activations Density 0.007%

    No Known Activations