© 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. 21476
    Prev
    Next
    INDEX
    Explanations

    trouble and difficulty

    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
     Helm
    -0.08
    ITU
    -0.08
    æī§æĶ¿
    -0.08
    IGO
    -0.08
    à¹Ĥà¸Ĺร
    -0.08
    åĸĿäºĨ
    -0.08
    ROL
    -0.08
    xon
    -0.08
    -inc
    -0.08
    MW
    -0.07
    POSITIVE LOGITS
    麻çĥ¦
    0.11
    ortho
    0.10
    æŁ¥æĺİ
    0.09
    æĽ´ä½ķåĨµ
    0.09
    ä½ķåĨµ
    0.09
    西æ´ĭ
    0.09
    è§ħ
    0.09
    Æ°a
    0.09
    è¿ĺä¸įå¦Ĥ
    0.09
    _chg
    0.09
    Activations Density 0.096%

    No Known Activations