© 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. 42278
    Prev
    Next
    INDEX
    Explanations

    not

    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
     either
    -0.44
    either
    -0.43
     Either
    -0.43
    Either
    -0.40
     EITHER
    -0.33
    Even
    -0.28
     long
    -0.28
     even
    -0.28
    çĶļèĩ³
    -0.28
    è·Łä½ł
    -0.27
    POSITIVE LOGITS
    æ±ľ
    0.35
     beneath
    0.28
     here
    0.26
    archives
    0.25
    ierte
    0.25
    nement
    0.25
    .opensource
    0.24
     abruptly
    0.24
    .PIPE
    0.24
    -Smith
    0.24
    Activations Density 0.001%

    No Known Activations