© 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. 9487
    Prev
    Next
    INDEX
    Explanations

    Company names or legal documents

    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
    ev
    -0.28
     Absolute
    -0.27
    eso
    -0.26
     abs
    -0.26
     Evolution
    -0.26
     tags
    -0.25
     absolute
    -0.25
     Ev
    -0.25
    tags
    -0.25
     mon
    -0.25
    POSITIVE LOGITS
    isses
    0.27
    å½ĵåľ°äºº
    0.26
     blasted
    0.23
    selectAll
    0.23
    ()},↵
    0.23
    ç²¾éĢļ
    0.23
    ittel
    0.23
    使çĶ¨ç¶²è·¯
    0.23
    æľĢå°ij
    0.23
    opian
    0.23
    Activations Density 0.016%

    No Known Activations