© 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. 19703
    Prev
    Next
    INDEX
    Explanations

    fanatic, tuberculosis, invention

    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
    åİī
    -0.09
    ลา
    -0.09
    ERY
    -0.08
    fant
    -0.08
    kte
    -0.08
    æĭ¬
    -0.08
    èĤī
    -0.08
    åĢŁ
    -0.08
    COND
    -0.08
    anni
    -0.08
    POSITIVE LOGITS
    æ°Ķæģ¯
    0.10
     frais
    0.10
    è¦ģ好好
    0.10
    çݰ身
    0.09
    uchar
    0.09
    åıijæī¬
    0.09
    亲åĪĩ
    0.09
    èIJĺ
    0.09
    åĪ¤
    0.09
    羣æŃ£
    0.09
    Activations Density 0.043%

    No Known Activations