© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 112173
    Prev
    Next
    INDEX
    Explanations

    Connector words

    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
    åłĤ
    -0.28
    oble
    -0.27
    thumbs
    -0.26
    allele
    -0.24
    alle
    -0.24
    ONUS
    -0.24
    overall
    -0.23
     hairs
    -0.23
    åŀĵ
    -0.23
    俾
    -0.23
    POSITIVE LOGITS
    uran
    0.28
    ált
    0.27
    ário
    0.27
    ergus
    0.26
    Stage
    0.25
    ilia
    0.24
    æľ¬æĽ¸
    0.24
     Stage
    0.24
     Synthetic
    0.23
    以æĿ¥
    0.23
    Activations Density 0.022%

    No Known Activations