© 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. 32-TRANSCODER-HP
    7. 41930
    Prev
    Next
    INDEX
    Explanations

    equals sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _drv
    -0.26
    è¯įæĿ¡
    -0.25
    ,),
    -0.25
     buc
    -0.24
    (?:
    -0.24
    undler
    -0.24
     controller
    -0.24
     fırsat
    -0.24
    flight
    -0.24
     `%
    -0.23
    POSITIVE LOGITS
    =
    0.50
    +
    0.47
    +a
    0.43
    ==
    0.38
    }=
    0.36
    =a
    0.36
    =-
    0.35
    )=
    0.35
    =back
    0.35
    ']=
    0.35
    Activations Density 0.004%

    No Known Activations