© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88983
    Prev
    Next
    INDEX
    Explanations

    manufactured materials and parts

    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
    Negative Logits
    cÃŃ
    -0.27
    å®ŀéĻħæĥħåĨµ
    -0.26
    åİļ
    -0.26
    à¹Ģà¸Ł
    -0.26
    =tk
    -0.25
    è·Ŀ
    -0.25
    amil
    -0.25
    è¾ij
    -0.24
    /sl
    -0.24
    quiz
    -0.23
    POSITIVE LOGITS
    esus
    0.31
    etes
    0.25
    à°Ĺ
    0.25
    ä¸įéĶĻ
    0.24
    å½Ģ
    0.24
    ä½Ĩæĺ¯å¯¹äºİ
    0.24
    ouro
    0.23
     uda
    0.23
    	constructor
    0.23
     одеж
    0.23
    Activations Density 0.017%

    No Known Activations