© 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. 30-TRANSCODER-HP
    7. 96846
    Prev
    Next
    INDEX
    Explanations

    non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĭ¤
    -0.28
    æĻºæħ§
    -0.27
    der
    -0.27
    å¾Ĵ
    -0.26
    kl
    -0.25
    å¢ŀ
    -0.25
     truth
    -0.25
    è¡į
    -0.24
    vn
    -0.24
     Kel
    -0.24
    POSITIVE LOGITS
    æĹ¶ä»£ä¸ŃåĽ½
    0.30
    ochen
    0.30
     بÙĥ
    0.28
    沪
    0.26
    (pe
    0.26
    ä¸įçĦ¶
    0.26
    åļ
    0.26
    herits
    0.25
    ibur
    0.25
    åĮ¯
    0.25
    Activations Density 0.937%

    No Known Activations