© 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. 98925
    Prev
    Next
    INDEX
    Explanations

    Copyright

    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
     PARAMETERS
    -0.28
    .dep
    -0.26
    纨
    -0.25
    ctest
    -0.25
    بÙĩ
    -0.25
    urette
    -0.24
    -Ray
    -0.24
    .omg
    -0.24
    Į¨
    -0.24
    被æīĵ
    -0.24
    POSITIVE LOGITS
    s
    0.33
    x
    0.28
    们
    0.27
    .Direct
    0.26
    åı¯ä»¥çĽ´æİ¥
    0.26
    gx
    0.26
    ÐĤ
    0.26
    éĻħ
    0.24
    ynthesis
    0.24
    ä¼ĺéĢī
    0.24
    Activations Density 0.028%

    No Known Activations