© 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. 14-TRANSCODER-HP
    7. 41430
    Prev
    Next
    INDEX
    Explanations

    Requests and/or assistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    模æĭŁ
    -0.29
    ither
    -0.29
    èĥ¶
    -0.27
    Pick
    -0.25
    asha
    -0.25
    å±ĬæŶ
    -0.25
    欢è¿İ
    -0.25
     lu
    -0.25
    fea
    -0.25
     duration
    -0.24
    POSITIVE LOGITS
    egade
    0.28
     chased
    0.26
    gmt
    0.26
    aurant
    0.26
    墨西åĵ¥
    0.26
    ç»ĻäºĨæĪij
    0.25
    urus
    0.25
    edException
    0.25
    ç«¿
    0.25
    esson
    0.24
    Activations Density 0.154%

    No Known Activations