© 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. 38940
    Prev
    Next
    INDEX
    Explanations

    presence or absence

    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
    è¾Ĥ
    -0.11
    åIJ¬è¯Ŀ
    -0.10
    å¼ŁåħĦ
    -0.09
    以èī²
    -0.09
    æµ·æĬ¥
    -0.09
    åŁ¤
    -0.09
    åħį
    -0.09
     вок
    -0.09
    éĺ®
    -0.09
    _ipc
    -0.09
    POSITIVE LOGITS
    ä¸įåľ¨
    0.13
     elsewhere
    0.13
    åĩºçİ°åľ¨
    0.13
    åŃĺåľ¨äºİ
    0.12
    å·²ç»ıåľ¨
    0.12
    å·²åľ¨
    0.11
     appearing
    0.10
    åľ¨æĪijçļĦ
    0.10
    æĽ¾åľ¨
    0.09
    åľ¨å½ĵåľ°
    0.09
    Activations Density 0.264%

    No Known Activations