© 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. 97330
    Prev
    Next
    INDEX
    Explanations

    website cookie policies

    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
    æĭ¦
    -0.29
    åijĹ
    -0.29
    edb
    -0.28
    athlon
    -0.28
    ebb
    -0.27
    åĵªæĢķ
    -0.27
    iete
    -0.26
    åħį
    -0.26
    éĻIJ
    -0.25
    éĩİçĶŁ
    -0.25
    POSITIVE LOGITS
    degree
    0.28
    责任人
    0.25
     Cleaner
    0.25
    osen
    0.25
     Ink
    0.24
     cleaned
    0.24
    Extras
    0.24
     Degree
    0.24
    秤
    0.24
    å°Ĩè¾¾åĪ°
    0.23
    Activations Density 0.029%

    No Known Activations