© 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. 20-TRANSCODER-HP
    7. 141799
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utations
    -0.26
     persuasion
    -0.26
    åļĵ
    -0.25
     persu
    -0.25
    .AutoField
    -0.24
    æĵį
    -0.24
    endif
    -0.24
     Gast
    -0.24
    ä¹ĸä¹ĸ
    -0.23
    è½»è½»åľ°
    -0.23
    POSITIVE LOGITS
    bens
    0.28
     mest
    0.27
    cope
    0.26
    isclosed
    0.25
     bore
    0.25
    ilogue
    0.25
    abit
    0.24
    inch
    0.24
    ä¸İæŶ
    0.24
    sville
    0.24
    Activations Density 0.377%

    No Known Activations