© 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. 24-TRANSCODER-HP
    7. 151397
    Prev
    Next
    INDEX
    Explanations

    diverse subjects

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Suggestions
    -0.26
    eah
    -0.24
    eria
    -0.24
    ç»ıå¼Ģ
    -0.23
     bpp
    -0.23
     cores
    -0.22
    Apellido
    -0.22
    .band
    -0.22
    pii
    -0.22
     mh
    -0.22
    POSITIVE LOGITS
    ä¸Ĭå¸Ĥåħ¬åı¸
    0.26
    åĽŀ家
    0.26
    <a
    0.24
    lessly
    0.23
    èĤ¡ä»½
    0.23
    (nonatomic
    0.23
    Ñĥж
    0.23
     rebounds
    0.23
    isl
    0.22
    éĴ¥
    0.22
    Activations Density 1.206%

    No Known Activations