© 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. 42298
    Prev
    Next
    INDEX
    Explanations

    non-English text

    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
    æ¯ĵ
    -0.28
     ÑģпÑĢав
    -0.28
    dam
    -0.28
     run
    -0.27
     Tic
    -0.27
    ogenerated
    -0.26
     pickle
    -0.26
    tring
    -0.26
    娩
    -0.26
    xdc
    -0.26
    POSITIVE LOGITS
    æĬ¥ç¤¾
    0.28
    çĽ¸ä¿¡å¤§å®¶
    0.27
     nháºŃt
    0.27
    çģ¶
    0.26
    rose
    0.26
    宵
    0.26
    è±¹
    0.26
    åĨĽäºº
    0.26
     appreh
    0.26
    å®ŀåľ°
    0.26
    Activations Density 0.001%

    No Known Activations