© 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. 23896
    Prev
    Next
    INDEX
    Explanations

    cleaning

    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
     Äijô
    -0.26
    å´İ
    -0.26
    èĽĬ
    -0.26
     favour
    -0.26
    æ°Ĺãģ¥
    -0.26
    _INTERFACE
    -0.25
    iente
    -0.25
    åħ¥ãĤĬ
    -0.25
    merc
    -0.24
     bureaucr
    -0.24
    POSITIVE LOGITS
    æľ½
    0.28
    esimal
    0.26
     social
    0.26
    enary
    0.26
    eenth
    0.25
    çĽ¸å·®
    0.25
    .CASCADE
    0.25
    åįĬ个
    0.24
     fine
    0.24
     lar
    0.24
    Activations Density 0.001%

    No Known Activations