© 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. 54687
    Prev
    Next
    INDEX
    Explanations

    days of the week

    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
    Negative Logits
    å§Ķä¼ļ
    -0.30
    å·¥å§Ķ
    -0.26
    itals
    -0.25
    dt
    -0.25
    ocities
    -0.24
    iture
    -0.24
    conf
    -0.24
    afs
    -0.24
    acct
    -0.23
    ä¸ĩè¾Ĩ
    -0.23
    POSITIVE LOGITS
    tri
    0.31
    Ñħодим
    0.29
    rid
    0.29
    rons
    0.27
    æİĴè¡Įæ¦ľ
    0.26
    undra
    0.26
    ridge
    0.25
     tri
    0.25
     foam
    0.25
     plat
    0.25
    Activations Density 0.025%

    No Known Activations