© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37091
    Prev
    Next
    INDEX
    Explanations

    height and length dimensions

    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
    éĻĮçĶŁ
    -0.10
    adin
    -0.10
    çĪ¶åŃIJ
    -0.10
    èĥĮåĮħ
    -0.10
    roids
    -0.09
    è¾ĩ
    -0.09
    ç¼£
    -0.09
    æĭ³
    -0.09
    迳
    -0.09
    亲åŃIJ
    -0.09
    POSITIVE LOGITS
     Narendra
    0.09
    .Dom
    0.08
    èĤĩ
    0.08
    é«ĺå³°æľŁ
    0.08
    оÑĢÑĤ
    0.08
    Dup
    0.08
    éķĽ
    0.08
    _aliases
    0.08
    åĢ¬
    0.08
    å³°åĢ¼
    0.08
    Activations Density 0.207%

    No Known Activations