© 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. 55297
    Prev
    Next
    INDEX
    Explanations

    seeing or hearing outcomes

    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
    é»ijæļĹ
    -0.09
    åı¯ä»¥è¯´
    -0.09
    ãģķãģĦ
    -0.09
    è°Ī
    -0.09
    åijľ
    -0.08
     Wit
    -0.08
    odka
    -0.08
    óc
    -0.08
    ÑĪе
    -0.08
    @show
    -0.08
    POSITIVE LOGITS
    åIJĦå¼Ĥ
    0.11
    仪
    0.09
    趾
    0.09
    èĥ½æĬĬ
    0.09
    ç¾İ女
    0.09
    éĤ£äºĽ
    0.09
    å¼Ĥ
    0.09
    åIJĦåĽ½
    0.09
    è¾Ħ
    0.09
    åħ¬çĶ¨
    0.09
    Activations Density 0.019%

    No Known Activations