© 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. 33-TRANSCODER-HP
    7. 52721
    Prev
    Next
    INDEX
    Explanations

    fluorescence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    uki
    -0.29
    UGC
    -0.28
    ANI
    -0.28
    sat
    -0.26
    yw
    -0.26
    ouri
    -0.26
    micro
    -0.26
     ub
    -0.26
    uby
    -0.25
    esters
    -0.25
    POSITIVE LOGITS
    inder
    0.31
    omer
    0.30
    å°±åľ¨äºİ
    0.29
    åıĭè°Ĭ
    0.28
    orm
    0.27
    æ´ģ
    0.26
    idget
    0.26
    osten
    0.26
    èį·
    0.25
    Signature
    0.24
    Activations Density 0.006%

    No Known Activations