© 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. 30970
    Prev
    Next
    INDEX
    Explanations

    review and audit contexts

    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
     bund
    -0.08
    æŃĩ
    -0.08
    auen
    -0.08
    äºĭä¸ļåıijå±ķ
    -0.08
    æĪ´
    -0.08
    æķĪ
    -0.08
    æķĪçĽĬ
    -0.08
    aines
    -0.08
    ç»
    -0.08
    éĥĬ
    -0.08
    POSITIVE LOGITS
    å®¡æŁ¥
    0.14
    è¯Ħ审
    0.14
    å®¡æł¸
    0.14
    åıĹçIJĨ
    0.13
    ãĥ¬ãĥĵãĥ¥ãĥ¼
    0.12
     reviewer
    0.12
    审çIJĨ
    0.12
    审
    0.12
     review
    0.12
    審
    0.11
    Activations Density 0.113%

    No Known Activations