© 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. 130845
    Prev
    Next
    INDEX
    Explanations

    Non-English terms

    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
    z
    -0.26
     Apprec
    -0.26
     True
    -0.25
    es
    -0.25
     mutating
    -0.25
    's
    -0.25
     Some
    -0.25
    de
    -0.24
    æªĶ
    -0.24
    ëŁī
    -0.24
    POSITIVE LOGITS
    å¼
    0.28
    _barrier
    0.27
    åĽº
    0.27
    éĤ£æł·
    0.26
    ngth
    0.25
    æĹłè®ºå¦Ĥä½ķ
    0.24
    plays
    0.24
    cry
    0.24
    prus
    0.24
    åı¹æģ¯
    0.24
    Activations Density 0.052%

    No Known Activations