© 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. 9246
    Prev
    Next
    INDEX
    Explanations

    Code and website snippets

    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
    ç¡®ä¿Ŀ
    -1.13
     ensure
    -0.96
     ensuring
    -0.95
    ä¿Ŀè¯ģ
    -0.93
     ensures
    -0.91
     ensured
    -0.89
    Ensure
    -0.86
     Ensure
    -0.86
    確ä¿Ŀ
    -0.82
     Ens
    -0.79
    POSITIVE LOGITS
    åı¯ä»¥å¸®åĬ©
    0.26
    å¾ĩ
    0.25
     Tits
    0.25
     tiá»ģn
    0.25
     offen
    0.25
    该æĢİä¹ĪåĬŀ
    0.25
    icers
    0.25
     Dane
    0.24
     Hilfe
    0.23
    Cour
    0.23
    Activations Density 0.000%

    No Known Activations