© 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. 41343
    Prev
    Next
    INDEX
    Explanations

    bio

    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
    ä»»
    -0.28
    viron
    -0.25
    大家ä¸Ģèµ·
    -0.25
    æĭĨ
    -0.25
    æĭį
    -0.25
    Êĥ
    -0.24
     obligated
    -0.24
    æµĭè¯Ħ
    -0.24
    ç«ŀäºīåĬĽ
    -0.24
     intensive
    -0.23
    POSITIVE LOGITS
     based
    0.29
    éģĹå¿ĺ
    0.28
     Based
    0.27
    pson
    0.26
    based
    0.26
    åŁºäºİ
    0.26
    .preference
    0.24
     par
    0.24
    newValue
    0.24
    å²Ń
    0.23
    Activations Density 0.005%

    No Known Activations