© 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. 141140
    Prev
    Next
    INDEX
    Explanations

    biographical entries

    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
    aber
    -0.28
    éĢĨ
    -0.28
    yleft
    -0.27
     Geh
    -0.26
    aben
    -0.26
    AGED
    -0.26
     COUNT
    -0.25
    age
    -0.25
    izio
    -0.25
     bip
    -0.24
    POSITIVE LOGITS
    åĽ´è§Ĥ
    0.28
    าะ
    0.26
    textures
    0.25
    [".
    0.25
     qualifier
    0.25
    çĸijä¼¼
    0.24
    å¾Ī大ç¨ĭ度
    0.24
    æ»ļ
    0.24
    æĮĤ
    0.24
    åľĪåŃIJ
    0.24
    Activations Density 31.022%

    No Known Activations