© 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. 112671
    Prev
    Next
    INDEX
    Explanations

    Sentimental topics

    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
     which
    -0.47
    which
    -0.43
    åĵª
    -0.38
    åĵªå®¶
    -0.37
    åĵªä¸ª
    -0.36
     коÑĤоÑĢой
    -0.36
     коÑĤоÑĢÑĭÑħ
    -0.36
     denen
    -0.36
     коÑĤоÑĢого
    -0.35
     Which
    -0.34
    POSITIVE LOGITS
     Santiago
    0.27
    ÑĤиÑĢов
    0.26
    odash
    0.25
    acci
    0.25
     repertoire
    0.24
    éĢłä»·
    0.23
     zÅĤ
    0.23
    kest
    0.23
    etched
    0.23
    etcode
    0.23
    Activations Density 0.007%

    No Known Activations