© 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. 35-TRANSCODER-HP
    7. 39785
    Prev
    Next
    INDEX
    Explanations

    partial words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åIJİæĿ¥
    -0.29
    )*/↵
    -0.27
    æīĵå¼ĢäºĨ
    -0.25
    çľ¼ä¸ĭ
    -0.25
    iqué
    -0.25
    å®ĮæĪIJäºĨ
    -0.24
    èĦļæŃ¥
    -0.24
    å¼ĢåIJ¯äºĨ
    -0.23
    æĻļå¹´
    -0.23
    ;*/↵
    -0.23
    POSITIVE LOGITS
    anka
    0.33
    rena
    0.31
    ren
    0.30
    ricia
    0.30
    mi
    0.29
    ccess
    0.28
    sta
    0.28
    rag
    0.28
    cca
    0.28
    lea
    0.28
    Activations Density 1.283%

    No Known Activations