© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38283
    Prev
    Next
    INDEX
    Explanations

    New Hampshire

    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
    æ©IJ
    -0.10
    饼
    -0.10
    åįĹæ²Ļ
    -0.09
    DBG
    -0.09
    -0.09
    arios
    -0.09
    chalk
    -0.09
    iew
    -0.09
     twilight
    -0.08
    çħ§å°Ħ
    -0.08
    POSITIVE LOGITS
    atory
    0.10
    åĢĻ
    0.10
    ments
    0.09
    ç¯ģ
    0.09
    人éĹ´
    0.09
    人家
    0.08
    åIJĦè¡Į
    0.08
    åĢ¦
    0.08
    -born
    0.08
    çĦ¶æĺ¯
    0.08
    Activations Density 0.016%

    No Known Activations