© 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. 39784
    Prev
    Next
    INDEX
    Explanations

    court documents, journals

    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
    éĴĬ
    -0.29
    侧éĿ¢
    -0.27
    uto
    -0.27
     oneself
    -0.26
    emp
    -0.25
    ä¸Ģ页
    -0.25
    RAIN
    -0.25
     screws
    -0.24
    éĺ±
    -0.24
    éĻIJ
    -0.24
    POSITIVE LOGITS
    ìĹ¼
    0.28
     hands
    0.27
    æľĹ
    0.26
     consolid
    0.25
    hatt
    0.25
     fair
    0.25
    cies
    0.24
    åłĤ
    0.24
    人æ°Ķ
    0.24
    ost
    0.23
    Activations Density 0.217%

    No Known Activations