© 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. 97603
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    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
     (
    -0.77
    ï¼Ī
    -0.65
     ("
    -0.51
    ä¹Łå°±æĺ¯
    -0.51
     ('
    -0.51
     ($
    -0.50
     (“
    -0.48
     (`
    -0.47
     (\
    -0.46
     (.
    -0.46
    POSITIVE LOGITS
    æĸ¹éĿ¢
    0.26
    侥幸
    0.24
    ])(
    0.23
    mvc
    0.23
    tons
    0.23
    æ°ijèĪª
    0.23
    #ad
    0.23
    sterdam
    0.23
    :"-
    0.23
    æĪijä¼ļ
    0.23
    Activations Density 0.007%

    No Known Activations