© 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. 32-TRANSCODER-HP
    7. 42367
    Prev
    Next
    INDEX
    Explanations

    asil

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Attach
    -0.29
    ckeditor
    -0.27
    ndl
    -0.26
     Rochester
    -0.26
    çľĭå¾Ĺ
    -0.26
     Attached
    -0.25
    çİĩ为
    -0.25
    åįıä¼ļä¼ļåijĺ
    -0.25
     freder
    -0.25
    INC
    -0.25
    POSITIVE LOGITS
    èĤ¡ç¥¨
    0.28
    ÅĤaw
    0.28
    çĵ¢
    0.28
    Mask
    0.27
    ä¸ĵè¾ij
    0.27
    mask
    0.27
     Zw
    0.26
     masking
    0.26
     Liber
    0.25
     Hayden
    0.25
    Activations Density 0.001%

    No Known Activations