© 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. 9821
    Prev
    Next
    INDEX
    Explanations

    freedom of speech and inquiry

    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
    çľĩ
    -0.09
    lez
    -0.09
    éĺį
    -0.09
    è´¶
    -0.09
    åĦ¿
    -0.08
    åºŁæ°Ķ
    -0.08
    é£ŀè·ĥ
    -0.08
    笥
    -0.08
    åı¯èĥ½æĢ§
    -0.08
    æµij
    -0.08
    POSITIVE LOGITS
    bsd
    0.10
     пеÑĩ
    0.09
    è´¢
    0.09
    æĦ§
    0.08
    åħħ足
    0.08
     ÑįÑĤ
    0.08
    ended
    0.08
    çļĦèĥĮåIJİ
    0.08
     UNIT
    0.08
    é¼ĵ
    0.08
    Activations Density 0.013%

    No Known Activations