© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 129293
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    ):-
    -0.29
    èĦı
    -0.27
     lak
    -0.25
     Hao
    -0.25
    reach
    -0.25
    uÅŁ
    -0.25
     polo
    -0.25
     bureaucr
    -0.24
     purse
    -0.24
    已达
    -0.24
    POSITIVE LOGITS
    âĸ¼
    0.26
    ilty
    0.26
    opy
    0.26
    opathy
    0.25
    rä
    0.25
    PG
    0.25
     Ret
    0.25
    occus
    0.24
     spelled
    0.24
    cession
    0.24
    Activations Density 0.984%

    No Known Activations