© 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. 17008
    Prev
    Next
    INDEX
    Explanations

    absence of something followed by a requirement

    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
    èĢĮä¸įæĺ¯
    -0.11
    ä¹Łåıªèĥ½
    -0.10
    解éĻ¤
    -0.09
    ä¸įæĩĪ
    -0.09
     rather
    -0.09
    ä¸įåĨį
    -0.09
    ä¸Ģ个éĹ®é¢ĺ
    -0.08
    åIJĦåľ°
    -0.08
    ä¸Ģ对ä¸Ģ
    -0.08
    æľĪä¸ĭ
    -0.08
    POSITIVE LOGITS
     سÙĪÙī
    0.16
     whatsoever
    0.13
    çIJĨä¼ļ
    0.13
    æľīä»»ä½ķ
    0.13
    except
    0.12
     anymore
    0.11
    theless
    0.10
    åĪ»æĦı
    0.10
    èĢĮæĺ¯
    0.10
    ä¾ĭå¤ĸ
    0.09
    Activations Density 0.053%

    No Known Activations