© 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. 129517
    Prev
    Next
    INDEX
    Explanations

    Technical descriptions/documentation

    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
    âĢ¦)↵↵
    -0.30
    /aws
    -0.29
    .stub
    -0.27
    æļ´éľ²
    -0.26
    游æĪıä¸Ń
    -0.26
    该游æĪı
    -0.26
    ril
    -0.25
    _games
    -0.25
    ÑĨен
    -0.24
    fila
    -0.24
    POSITIVE LOGITS
    unken
    0.25
    .then
    0.25
    matches
    0.25
    method
    0.25
    ething
    0.24
    ãĤĤãĤī
    0.24
    çĦ¶åIJİ
    0.24
     Ñıн
    0.24
    èµĦ产è¯Ħä¼°
    0.24
    åĥįãģį
    0.24
    Activations Density 1.182%

    No Known Activations