© 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. 97214
    Prev
    Next
    INDEX
    Explanations

    S

    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
    fax
    -0.28
    éĤ¸
    -0.26
    ities
    -0.25
    .Results
    -0.25
    ãĤ«ãĥ«
    -0.25
    åĬį
    -0.25
     individual
    -0.25
    [--
    -0.24
    Individual
    -0.24
    ieri
    -0.24
    POSITIVE LOGITS
    Assembly
    0.27
     fork
    0.26
    ushman
    0.26
    unchecked
    0.25
    æĪIJå°±
    0.25
    éĢı
    0.24
    аÑĪ
    0.24
    ersistence
    0.24
     pom
    0.23
    asset
    0.23
    Activations Density 0.003%

    No Known Activations