© 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. 33317
    Prev
    Next
    INDEX
    Explanations

    up to date

    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
    fund
    -0.10
    æħķ
    -0.10
    æ¯Ļ
    -0.09
    çł´
    -0.09
    çĪ±ç¾İ
    -0.09
     maté
    -0.09
    ç£ħ
    -0.09
    ubb
    -0.08
    éĻ©
    -0.08
    å«Į
    -0.08
    POSITIVE LOGITS
    赶ä¸Ĭ
    0.10
    èĤļ
    0.10
     cáºŃp
    0.09
    arus
    0.08
    èµ·æĿ¥äºĨ
    0.08
    æĽ´æĸ°
    0.08
    å®Į
    0.08
    ä¸İæĹ¶ä¿±è¿Ľ
    0.08
    åħĪè¿ĽæĬĢæľ¯
    0.08
    ilan
    0.08
    Activations Density 0.050%

    No Known Activations