© 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. 27-TRANSCODER-HP
    7. 8208
    Prev
    Next
    INDEX
    Explanations

    perpendicular

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Stroke
    -0.26
    edException
    -0.25
    quals
    -0.25
    èĩªçĦ¶ä¿ĿæĬ¤
    -0.25
    caled
    -0.25
    饰æ¼Ķ
    -0.24
    _translate
    -0.24
    æĮ¯ãĤĬ
    -0.24
    Stroke
    -0.24
    èĮĥåĽ´
    -0.24
    POSITIVE LOGITS
    s
    0.54
    solver
    0.33
    squ
    0.30
    sand
    0.29
    spl
    0.28
    sist
    0.27
    sns
    0.27
    sdk
    0.27
    sampling
    0.27
    sar
    0.27
    Activations Density 0.015%

    No Known Activations