© 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. 58261
    Prev
    Next
    INDEX
    Explanations

    high degree and impact

    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
    åıĻ
    -0.09
    éĺ¿éĩĮ
    -0.08
    è¶Ĭ
    -0.08
    å°±è¶Ĭ
    -0.08
    æ»ĥ
    -0.08
    á»ijt
    -0.08
    LEN
    -0.08
    æĹ¥èĩ³
    -0.08
     Bounds
    -0.08
    主è¦ģ
    -0.08
    POSITIVE LOGITS
    ç¥ŀç»ıç³»ç»Ł
    0.09
    uras
    0.09
     glimpse
    0.09
    æ§ģ
    0.09
    çĶŁæ´»çݯå¢ĥ
    0.08
    èµĽåŃ£
    0.08
    èĪĮå°ĸ
    0.08
    sei
    0.08
     rider
    0.08
    rides
    0.08
    Activations Density 0.229%

    No Known Activations