© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4443
    Prev
    Next
    INDEX
    Explanations

    outlaw, exiled, lawless

    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
    æ²ģ
    -0.09
    =default
    -0.09
    积æŀģåıĤä¸İ
    -0.08
    lessly
    -0.08
    eller
    -0.08
    ãĤĵãģª
    -0.08
    issing
    -0.08
    ongs
    -0.08
    IVITY
    -0.08
    -day
    -0.08
    POSITIVE LOGITS
    å¼¢
    0.09
    growth
    0.09
     ÑģиÑĤ
    0.08
    åĽłä¸ºå¥¹
    0.08
    å·²ä¹ħçļĦ
    0.08
    оÑī
    0.08
    ä¸Ģ个éĩįè¦ģ
    0.08
    бÑĢо
    0.08
    าà¸ĩ
    0.08
    ry
    0.08
    Activations Density 0.009%

    No Known Activations