© 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. 8968
    Prev
    Next
    INDEX
    Explanations

    Copyright

    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
    ä¹ĭæĺŁ
    -0.29
    ä¸į失
    -0.27
    大éĿ¢ç§¯
    -0.26
     twins
    -0.25
    TECT
    -0.25
    stars
    -0.24
    æĽ´åĬł
    -0.24
    ạm
    -0.24
    uble
    -0.24
     understandably
    -0.24
    POSITIVE LOGITS
    åĬĽ
    0.34
    à¹ģรà¸ĩ
    0.24
     Force
    0.24
     classical
    0.24
    rait
    0.24
    Labour
    0.24
     addition
    0.24
     bless
    0.24
    liga
    0.24
     comparison
    0.23
    Activations Density 0.171%

    No Known Activations