© 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. 63457
    Prev
    Next
    INDEX
    Explanations

    Long sentences

    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
    åıį
    -0.28
    çľĭæĿ¥
    -0.28
    amm
    -0.25
    èĢĮè¨Ģ
    -0.25
    (OP
    -0.25
    (MouseEvent
    -0.25
    å²Ķ
    -0.25
     IPPROTO
    -0.25
    YP
    -0.24
     Ori
    -0.24
    POSITIVE LOGITS
    ogonal
    0.29
    è´¨éĩıåĴĮ
    0.25
    ç³ĸå°¿
    0.25
    æ¼ĶåĶ±
    0.24
    çĹĴ
    0.24
     push
    0.24
    Invariant
    0.23
     ov
    0.23
    _ELEMENT
    0.23
    å¢Ł
    0.23
    Activations Density 22.259%

    No Known Activations