© 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. 22-TRANSCODER-HP
    7. 112614
    Prev
    Next
    INDEX
    Explanations

    AM/PM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edm
    -0.27
    -letter
    -0.26
    atre
    -0.26
     {?}
    -0.26
    ater
    -0.25
    uppe
    -0.25
    peak
    -0.24
    ville
    -0.24
    ERP
    -0.24
    -spacing
    -0.23
    POSITIVE LOGITS
    åľ¨ç½ij绾
    0.27
    pton
    0.26
    ä¹³
    0.25
     detain
    0.24
    以æѤ
    0.24
    æĦıè¯Ĩå½¢æĢģ
    0.23
     knock
    0.23
    æĹ¥å¸¸
    0.23
    prox
    0.22
     Years
    0.22
    Activations Density 0.054%

    No Known Activations