© 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. 57973
    Prev
    Next
    INDEX
    Explanations

    organizations and licenses

    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
    çıł
    -0.26
    åĪ¨
    -0.25
    .isnan
    -0.25
    .SizeType
    -0.25
     doubt
    -0.25
     beads
    -0.23
    ×ĵ×ķר
    -0.23
    -instance
    -0.23
    LESS
    -0.23
    epam
    -0.23
    POSITIVE LOGITS
    æ·Ĩ
    0.30
    qm
    0.29
    ç¼ļ
    0.28
    æijĨèĦ±
    0.27
    èµĦæºIJéħįç½®
    0.26
    äºī龸
    0.25
    _FEATURE
    0.25
    çĶ¨æĪ·ä½ĵéªĮ
    0.25
    çijĻ
    0.24
    oline
    0.24
    Activations Density 0.001%

    No Known Activations