© 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. 43545
    Prev
    Next
    INDEX
    Explanations

    the

    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
    âĩĵ
    -0.26
     nineteen
    -0.26
    TOOLS
    -0.26
    æ¯ı个人éĥ½
    -0.24
    izen
    -0.24
    ICLE
    -0.24
    iker
    -0.24
    ools
    -0.23
    è¿Ļ对
    -0.23
    icos
    -0.23
    POSITIVE LOGITS
    两
    0.58
     two
    0.52
     Two
    0.49
    两个
    0.46
    two
    0.46
    两家
    0.45
    åħ©
    0.44
    _two
    0.43
     duas
    0.43
    Two
    0.43
    Activations Density 0.002%

    No Known Activations