© 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. 99193
    Prev
    Next
    INDEX
    Explanations

    Technical documents/code

    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
    个ä½ĵ
    -0.27
     dies
    -0.26
     die
    -0.26
    feit
    -0.26
    onacci
    -0.26
    è·³åĩº
    -0.25
    ÃĵN
    -0.25
    ä¸ĵæłı
    -0.25
    æ¶ĪçģŃ
    -0.24
    lessly
    -0.24
    POSITIVE LOGITS
    ParameterValue
    0.26
    onga
    0.24
     benefited
    0.24
    .SIG
    0.24
    anness
    0.24
    .rf
    0.24
    æĺŃ
    0.23
     ControllerBase
    0.23
    .references
    0.23
    rente
    0.23
    Activations Density 0.002%

    No Known Activations