© 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. 42277
    Prev
    Next
    INDEX
    Explanations

    World

    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
     mes
    -0.29
    å§ľ
    -0.28
    iphy
    -0.26
    è¹ĩ
    -0.26
    apy
    -0.26
    _mes
    -0.25
    åİ¥
    -0.25
    mes
    -0.25
    工人
    -0.25
    ä¸ĢåĪĩ
    -0.24
    POSITIVE LOGITS
    åĬŀ
    0.28
     pard
    0.27
    äºĭ實
    0.25
    etr
    0.25
    辦
    0.25
    家éķ¿ä»¬
    0.24
    pty
    0.24
    ngo
    0.24
    ем
    0.24
    FACT
    0.24
    Activations Density 0.001%

    No Known Activations