© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53441
    Prev
    Next
    INDEX
    Explanations

    buildings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ°ijéĹ´
    -0.27
    ãģķ
    -0.27
    社交
    -0.26
    ä½ı
    -0.25
    cred
    -0.25
    èģĮä¸ļ
    -0.25
    秣
    -0.25
    aveled
    -0.25
    楼ä¸ĭ
    -0.24
    æĪ¿ä¸ľ
    -0.24
    POSITIVE LOGITS
    stri
    0.30
     dice
    0.27
    heiten
    0.26
     bt
    0.26
    _CTX
    0.25
     wards
    0.25
    ç°¿
    0.25
     bites
    0.25
    åı¸
    0.25
    presso
    0.24
    Activations Density 0.006%

    No Known Activations