© 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. 19-TRANSCODER-HP
    7. 8548
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     preference
    -0.25
    á»ĩp
    -0.25
     dep
    -0.25
    ำ
    -0.25
    .ut
    -0.24
    <y
    -0.24
     preferences
    -0.24
    mart
    -0.23
    arton
    -0.23
     cosy
    -0.23
    POSITIVE LOGITS
     Pav
    0.27
    ä¸įè§ģ
    0.27
    Deal
    0.26
    åĪĿæľŁ
    0.24
    rogen
    0.24
    _Format
    0.24
    chte
    0.24
     deal
    0.23
    æŀķ
    0.23
    Format
    0.23
    Activations Density 0.014%

    No Known Activations