© 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. 33-TRANSCODER-HP
    7. 54204
    Prev
    Next
    INDEX
    Explanations

    gener/comp

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĢаÑģÑĤ
    -0.29
    rastructure
    -0.28
    rices
    -0.27
     aspir
    -0.27
    pector
    -0.27
     endors
    -0.26
    请åıĬæŶ
    -0.26
    hasil
    -0.25
    èįª
    -0.25
    .FLAG
    -0.25
    POSITIVE LOGITS
    æ±Ł
    0.33
    en
    0.31
    ä¼łè¾¾
    0.28
    ic
    0.27
    ä¸įåIJĪ
    0.27
    ate
    0.27
    <message
    0.26
    bol
    0.26
    ale
    0.25
     ure
    0.25
    Activations Density 0.005%

    No Known Activations