© 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. 128880
    Prev
    Next
    INDEX
    Explanations

    Most

    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
     thôi
    -0.26
    asis
    -0.26
    åĪĩ
    -0.25
    æŁłæª¬
    -0.25
    =len
    -0.23
    ä¸įåĩºæĿ¥
    -0.23
    .Slice
    -0.23
    iges
    -0.23
    ingo
    -0.23
    riott
    -0.23
    POSITIVE LOGITS
    æłı缮
    0.27
    otton
    0.25
     stro
    0.25
    óst
    0.25
    usters
    0.24
     climates
    0.24
    stro
    0.24
    æĸ¹æīį
    0.23
    ower
    0.23
    âĤĵ
    0.23
    Activations Density 0.012%

    No Known Activations