© 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. 42652
    Prev
    Next
    INDEX
    Explanations

    future events/plans

    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
    leh
    -0.26
     Last
    -0.25
     last
    -0.25
    chin
    -0.24
    å½¢
    -0.24
     Kare
    -0.23
    awi
    -0.23
    last
    -0.23
    pag
    -0.23
     bonding
    -0.23
    POSITIVE LOGITS
     any
    0.48
    ä»»ä½ķ
    0.45
     once
    0.38
    any
    0.37
    ANY
    0.37
     Any
    0.36
    Any
    0.36
    ä»»ä½ķå½¢å¼ı
    0.35
    ä»»ä½ķä¸Ģ个
    0.34
     well
    0.34
    Activations Density 0.007%

    No Known Activations