© 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. 23883
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     solution
    -0.30
    uer
    -0.29
    è´¡çĮ®
    -0.28
    -src
    -0.27
    _sy
    -0.25
    转åĮĸ为
    -0.25
    ÑģÑĮ
    -0.25
    解åĨ³éĹ®é¢ĺ
    -0.25
     conversation
    -0.25
    UITextField
    -0.24
    POSITIVE LOGITS
    peater
    0.29
     randomly
    0.27
     periodically
    0.27
     puberty
    0.26
    ocard
    0.26
    .oc
    0.26
     invaded
    0.25
    èįŁ
    0.25
    è¯ĸ
    0.23
    éģŃåĪ°
    0.23
    Activations Density 0.000%

    No Known Activations