© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7232
    Prev
    Next
    INDEX
    Explanations

    patio and courtyard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ings
    -0.12
    AFP
    -0.09
     çalÄ±ÅŁma
    -0.09
    ingly
    -0.09
    åĸī
    -0.09
    è¯Ī
    -0.09
    Styled
    -0.09
     Territory
    -0.08
    rien
    -0.08
    éħį件
    -0.08
    POSITIVE LOGITS
    工夫
    0.11
    åĬŁå¤«
    0.10
    éĨĴ缮
    0.10
    iles
    0.10
    ting
    0.10
    wards
    0.09
    andon
    0.09
    abras
    0.09
    ï¸
    0.09
    bull
    0.09
    Activations Density 0.002%

    No Known Activations