© 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. 38609
    Prev
    Next
    INDEX
    Explanations

    anytime

    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
    ÑĢаз
    -0.09
    çĪ
    -0.09
    èĥ¥
    -0.09
    æ´½
    -0.08
    çĩ®
    -0.08
     gì
    -0.08
    sel
    -0.08
    mith
    -0.08
    æĥħ人
    -0.08
    æķ´æķ´
    -0.08
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.11
    ASF
    0.09
    uffer
    0.09
    éĥ½æľīçĿĢ
    0.09
    вл
    0.09
    婧
    0.08
    åĬ¼
    0.08
    å¾ģæ±Ĥ
    0.08
    .hasMore
    0.08
    åıªè§ģ
    0.08
    Activations Density 0.004%

    No Known Activations