© 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. 33-TRANSCODER-HP
    7. 52809
    Prev
    Next
    INDEX
    Explanations

    offers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    大家ä¸Ģèµ·
    -0.28
    æĻķ
    -0.27
    éĻĤ
    -0.26
    让æ¶Īè´¹èĢħ
    -0.26
    å¸ĥèݱ
    -0.25
    ç´Ģ
    -0.25
    hal
    -0.25
    åĭ¿
    -0.25
     Ballard
    -0.24
     hurt
    -0.24
    POSITIVE LOGITS
     offers
    0.66
     Offers
    0.61
     offer
    0.48
    offers
    0.48
    Offers
    0.46
     deals
    0.43
    Offer
    0.40
     Offer
    0.39
    offer
    0.35
     ofrece
    0.35
    Activations Density 0.428%

    No Known Activations