© 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. 52095
    Prev
    Next
    INDEX
    Explanations

    Still today

    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
    eer
    -0.09
    uality
    -0.09
    itable
    -0.08
    utable
    -0.08
    atile
    -0.08
    å¿ĥ缮
    -0.08
    åı¦è¡Į
    -0.08
    icolor
    -0.08
     t
    -0.08
    å¾Ĺèµ·
    -0.08
    POSITIVE LOGITS
    hausen
    0.11
     اÙĦØ£Ùħر
    0.10
    çĥŃçĪ±
    0.10
    çķĻå®Ī
    0.09
    éĺ¶
    0.09
    ç¢İçīĩ
    0.09
    mania
    0.09
    åĴ¬
    0.09
    chez
    0.09
    RAINT
    0.09
    Activations Density 0.008%

    No Known Activations