© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59315
    Prev
    Next
    INDEX
    Explanations

    access or reach

    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
    Negative Logits
    æĸ§
    -0.10
    å½·
    -0.10
    èĤĸ
    -0.10
    ä¾Ŀæ³ķ
    -0.09
    æ³ķå®ļ
    -0.09
    æĨ¬
    -0.09
    渲
    -0.09
    ä¿¡å¿ĥ
    -0.09
     pin
    -0.09
    ä¸Ģè·¯
    -0.09
    POSITIVE LOGITS
     Reach
    0.14
    accessible
    0.13
    Reach
    0.13
    reachable
    0.13
     inaccessible
    0.13
    åı¯è¾¾
    0.13
     unreachable
    0.13
     доÑģÑĤÑĥп
    0.12
     reachable
    0.12
     reach
    0.12
    Activations Density 0.226%

    No Known Activations