© 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. 42197
    Prev
    Next
    INDEX
    Explanations

    way

    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
    ifer
    -0.29
    åĢŁ
    -0.28
    chluss
    -0.27
    èľķ
    -0.27
    å±±åİ¿
    -0.25
    ä¹ĭæĺŁ
    -0.24
    车åŃIJ
    -0.24
    人ãģ«
    -0.24
    ÑĨов
    -0.23
    heroes
    -0.23
    POSITIVE LOGITS
     way
    0.56
    way
    0.38
     Way
    0.35
    æĸ¹å¼ı
    0.34
    Way
    0.33
    _way
    0.32
     approach
    0.31
     WAY
    0.29
    lys
    0.28
    .way
    0.28
    Activations Density 0.008%

    No Known Activations