© 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. 41480
    Prev
    Next
    INDEX
    Explanations

    vector

    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
     lips
    -0.30
    ç»Ŀä¸į
    -0.28
    ç»Ŀ对
    -0.28
    ért
    -0.27
    ullo
    -0.26
    æ·³
    -0.25
    ukkit
    -0.25
    etch
    -0.25
    .Prop
    -0.24
    .valueOf
    -0.24
    POSITIVE LOGITS
    atories
    0.27
    鼶ç¢İ
    0.27
    åıĪæľī
    0.26
    è§Ħå®ļçļĦ
    0.26
    æľīçĶ¨
    0.25
     fares
    0.24
    éĿŀ常éĢĤåIJĪ
    0.24
     mẫu
    0.24
    }while
    0.24
     okreÅĽ
    0.24
    Activations Density 1.276%

    No Known Activations