© 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. 56735
    Prev
    Next
    INDEX
    Explanations

    Register, .F.C.F.R., Project-wide, Union

    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
    Fred
    -0.08
    ISC
    -0.08
     Mahmoud
    -0.08
    åĿĬ
    -0.08
    _intf
    -0.08
    íĩ´
    -0.08
    Principal
    -0.08
    Void
    -0.08
    angling
    -0.08
    æİ¥è¿ĩ
    -0.07
    POSITIVE LOGITS
    è¯Ħè®®
    0.11
    æĺ¯æĪijçļĦ
    0.11
    åı¬åĽŀ
    0.10
    æĽĻåħī
    0.10
    æŶæŶ
    0.09
    åĽŀå¤į
    0.09
    管çIJĨå·¥ä½ľ
    0.09
    åħĪè¿ĽæĬĢæľ¯
    0.09
    ç«ĭãģ¦
    0.09
    çĽijçĿ£ç®¡çIJĨ
    0.09
    Activations Density 0.145%

    No Known Activations