© 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. 27-TRANSCODER-HP
    7. 58106
    Prev
    Next
    INDEX
    Explanations

    Names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phan
    -0.28
    _DRV
    -0.27
     Got
    -0.26
    _cred
    -0.26
    çīĮåŃIJ
    -0.25
    Posts
    -0.25
    uhn
    -0.25
    endra
    -0.25
    epad
    -0.25
     flatten
    -0.25
    POSITIVE LOGITS
    ØŃÙħا
    0.29
     mast
    0.26
    ç¿Ĵ
    0.26
    è°ĭ
    0.26
    åij½ä¸Ń
    0.26
    keiten
    0.25
     Mast
    0.25
     PIE
    0.25
    staking
    0.25
    AffineTransform
    0.25
    Activations Density 1.068%

    No Known Activations