© 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. 12-TRANSCODER-HP
    7. 23935
    Prev
    Next
    INDEX
    Explanations

    founding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĥĬ人
    -0.31
    joy
    -0.28
     wol
    -0.26
    æ¸ĹéĢı
    -0.26
     Pen
    -0.26
    inkel
    -0.25
     fullest
    -0.24
     AssemblyVersion
    -0.24
     fisse
    -0.23
    å·¦åı³
    -0.23
    POSITIVE LOGITS
    cards
    0.27
    rics
    0.26
    ynom
    0.26
    ãĥ¡ãĥĩãĤ£
    0.25
    庵
    0.24
    éĢĿ
    0.24
    ards
    0.24
    æĭ¥
    0.24
    abei
    0.24
     UInt
    0.24
    Activations Density 0.010%

    No Known Activations