© 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. 51625
    Prev
    Next
    INDEX
    Explanations

    template declaration

    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
    kits
    -0.10
    å°±è¿ij
    -0.09
    geries
    -0.09
    é«
    -0.09
    kit
    -0.08
    ivec
    -0.08
    ëłī
    -0.08
    ìĤ¬íķŃ
    -0.08
    ieg
    -0.08
    ç²Ĺ
    -0.08
    POSITIVE LOGITS
    çĴł
    0.09
    SUP
    0.09
    éĹ®é¢ĺæĺ¯
    0.08
    åŃĹ第
    0.08
    å°ıç¼ĸ
    0.08
    -away
    0.08
    éĺģ
    0.08
    erah
    0.08
    orem
    0.08
     nerd
    0.08
    Activations Density 0.167%

    No Known Activations