© 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. 130311
    Prev
    Next
    INDEX
    Explanations

    economics

    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
    åįıå®ļ
    -0.27
    -interest
    -0.27
    ritel
    -0.27
    æĺ¯æ¯Ķè¾ĥ
    -0.27
    æ²£
    -0.27
     foreigners
    -0.26
    ä¹Łæ¯Ķè¾ĥ
    -0.26
     rit
    -0.26
    :bg
    -0.26
    åī½
    -0.26
    POSITIVE LOGITS
    Ĥ¬
    0.28
    PU
    0.28
    uvw
    0.27
    SK
    0.27
    ergy
    0.26
    leness
    0.25
    isons
    0.25
    appers
    0.24
    ç³»
    0.24
    psy
    0.24
    Activations Density 0.006%

    No Known Activations