© 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. 31839
    Prev
    Next
    INDEX
    Explanations

    Indian states and regions

    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
    èĮħ
    -0.09
    èįīåľ°
    -0.09
    utes
    -0.09
    æIJŃ
    -0.09
    笪
    -0.09
    çĽİ
    -0.08
     lawn
    -0.08
     masc
    -0.08
     patched
    -0.08
    rab
    -0.08
    POSITIVE LOGITS
    æĪı
    0.11
    Specifier
    0.10
    pher
    0.10
    æŀģé«ĺ
    0.09
    Tho
    0.09
    è¿Ļæīį
    0.09
    åĨ°éĽª
    0.09
    çľīæ¯Ľ
    0.09
     hazard
    0.09
    è¶Ĭé«ĺ
    0.09
    Activations Density 0.024%

    No Known Activations