© 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. 25-TRANSCODER-HP
    7. 109212
    Prev
    Next
    INDEX
    Explanations

    anniversary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ones
    -0.32
    ONES
    -0.27
    ones
    -0.26
    åijĺ
    -0.25
    iw
    -0.24
    except
    -0.24
    ertain
    -0.24
    è§ģéĿ¢
    -0.24
    _ve
    -0.23
    ัส
    -0.23
    POSITIVE LOGITS
    éĺī
    0.27
    (today
    0.26
    çİ»
    0.26
     metall
    0.26
    ADB
    0.25
    Äħc
    0.25
    ä»Ĭ天
    0.24
    –and
    0.24
     «
    0.24
    æŶéĹ´ä¸º
    0.24
    Activations Density 0.133%

    No Known Activations