© 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. 57153
    Prev
    Next
    INDEX
    Explanations

    hands

    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
    upe
    -0.29
     Feinstein
    -0.28
    onen
    -0.27
     sit
    -0.27
    arat
    -0.26
    éļ°
    -0.26
    çĨŁ
    -0.26
    sla
    -0.26
    heet
    -0.24
    IGNORE
    -0.24
    POSITIVE LOGITS
     hands
    1.17
    hands
    0.91
    Hands
    0.89
     Hands
    0.89
    æīĭä¸Ĭ
    0.72
    æīĭ
    0.71
     manos
    0.69
    æīĭéĩĮ
    0.69
    æīĭä¸Ń
    0.69
    åıĮæīĭ
    0.66
    Activations Density 0.001%

    No Known Activations