© 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. 130418
    Prev
    Next
    INDEX
    Explanations

    old

    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
    aram
    -0.28
    vod
    -0.27
    asted
    -0.27
    oire
    -0.26
    ä¸Ĭåīį
    -0.25
     apresent
    -0.25
    宫
    -0.25
    è£ħ饰
    -0.24
    awe
    -0.24
    åĮħ
    -0.24
    POSITIVE LOGITS
     informant
    0.27
     Supern
    0.27
    碧æ¡ĤåĽŃ
    0.26
    scp
    0.26
    Utc
    0.25
    itics
    0.24
    usat
    0.24
    Growing
    0.23
     esl
    0.23
    growth
    0.23
    Activations Density 4.734%

    No Known Activations