© 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. 23894
    Prev
    Next
    INDEX
    Explanations

    cocktail and drink recipes

    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
    干货
    -0.11
    çĻŀ
    -0.10
    èĭij
    -0.10
    èijµ
    -0.10
    ä¸ĩçī©
    -0.09
    é«ĺéĢŁåħ¬è·¯
    -0.09
    éĽ¾éľ¾
    -0.09
    èĩªç§°
    -0.09
    rans
    -0.09
    çĸĿ
    -0.09
    POSITIVE LOGITS
     cocktails
    0.10
    ä¸ĢæĿ¯
    0.10
     cocktail
    0.09
     Cocktail
    0.09
    iaz
    0.09
    åĢĴå¡Į
    0.08
    çĽħ
    0.08
    åIJįçīĩ
    0.08
    åħļæĶ¿
    0.08
    åľ¨ä¸Ĭæµ·
    0.08
    Activations Density 0.058%

    No Known Activations