© 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. 86862
    Prev
    Next
    INDEX
    Explanations

    Spr

    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
     unsur
    -0.26
    incoming
    -0.26
    UIApplication
    -0.25
    ä¸īåŃ£åº¦
    -0.25
     incur
    -0.25
    éĢ»
    -0.25
    éĿŀ常çļĦ
    -0.25
     ste
    -0.25
    onical
    -0.24
     adolescence
    -0.24
    POSITIVE LOGITS
    åģ¶
    0.26
    lug
    0.25
    jur
    0.25
    rients
    0.24
    åĶģ
    0.24
    å¯Ħ
    0.24
    <![
    0.23
    lesi
    0.23
    TRIES
    0.23
    jan
    0.23
    Activations Density 0.001%

    No Known Activations