© 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. 8637
    Prev
    Next
    INDEX
    Explanations

    eyes

    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
    #
    -0.29
    åıĹ欢è¿İ
    -0.28
    ä¸į让
    -0.27
     habit
    -0.25
    Next
    -0.24
    ä¸ĢæĹ¥
    -0.24
    æŀľ
    -0.24
    ysis
    -0.24
    ä¸įå¿ĺ
    -0.24
    bery
    -0.24
    POSITIVE LOGITS
     eyes
    0.44
    çľ¼çĿĽ
    0.44
     eye
    0.41
    çŀ³
    0.38
    èĦ¸èī²
    0.38
    çľ¼
    0.38
     face
    0.36
    eyes
    0.35
    face
    0.35
    头
    0.35
    Activations Density 0.009%

    No Known Activations