© 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. 3974
    Prev
    Next
    INDEX
    Explanations

    spatial locations and containment

    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
    åľ¨åľ°ä¸Ĭ
    -0.11
    åľ¨åºĬä¸Ĭ
    -0.11
    åľ¨ä¸Ĭæµ·
    -0.10
    åľ¨ä¹İ
    -0.10
    èĥĮåIJİ
    -0.09
    åľ¨å®¶éĩĮ
    -0.09
    åľ¨åĮĹ京
    -0.09
    åľ¨è¿ĻéĩĮ
    -0.09
    åıĤä¸İåĪ°
    -0.09
     Bunny
    -0.09
    POSITIVE LOGITS
     Bra
    0.09
    以便
    0.08
    å°Ĩè¿Ľä¸ĢæŃ¥
    0.08
     spoiler
    0.08
    åģķ
    0.08
    åĬłæĭ¿å¤§
    0.07
     afin
    0.07
     Hur
    0.07
    ä½ľä¸ºä¸ĢåIJį
    0.07
    è¿ijå¹´æĿ¥
    0.07
    Activations Density 0.144%

    No Known Activations