© 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. 11875
    Prev
    Next
    INDEX
    Explanations

    Add or place

    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
    为ä¹ĭ
    -0.09
    å¸ĤåľºåĮĸ
    -0.09
    æ·±åĮĸæĶ¹éĿ©
    -0.09
    éħ¬
    -0.09
    çĻ½è¡£
    -0.08
    esh
    -0.08
     grooming
    -0.08
    éĶ¤
    -0.08
    è¹Ħ
    -0.08
    aret
    -0.08
    POSITIVE LOGITS
    åĬłåħ¥
    0.10
    è±Ĩçĵ£
    0.10
    -Sah
    0.09
    åĸľæ¬¢åIJĥ
    0.09
    htags
    0.09
    âĸ£
    0.09
    SearchParams
    0.09
    å¼ķ
    0.09
    ndl
    0.08
    æĹłå£°
    0.08
    Activations Density 0.151%

    No Known Activations