© 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. 35-TRANSCODER-HP
    7. 40574
    Prev
    Next
    INDEX
    Explanations

    say "ac"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    è¿ĺæľīä»Ģä¹Ī
    -0.28
    çĻ»è®°
    -0.28
    ä¸ĢæŶ
    -0.26
     Flint
    -0.26
    gy
    -0.25
    åħ¨æĹ¥
    -0.25
    lingen
    -0.25
    èĪª
    -0.24
    Lng
    -0.24
    /signup
    -0.23
    POSITIVE LOGITS
    /ac
    0.38
    acing
    0.35
    ac
    0.35
    acea
    0.34
     ac
    0.33
    (ac
    0.33
    acr
    0.32
    aced
    0.32
    aci
    0.32
    ACING
    0.31
    Activations Density 4.389%

    No Known Activations