© 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. 41827
    Prev
    Next
    INDEX
    Explanations

    l

    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
    满
    -0.26
     Mellon
    -0.26
     material
    -0.26
    亿ä¸ĩ
    -0.25
    )const
    -0.24
    _pad
    -0.24
     padr
    -0.24
    人æ°ijæ³ķéĻ¢
    -0.24
    rito
    -0.24
    udded
    -0.23
    POSITIVE LOGITS
    ny
    0.30
    oen
    0.29
    æĹ¥äº§
    0.28
    uner
    0.28
    als
    0.28
    çĤ¹äºĨ
    0.27
    çĹķ
    0.27
    缣
    0.27
    aneous
    0.26
    alse
    0.26
    Activations Density 0.001%

    No Known Activations