© 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. 61795
    Prev
    Next
    INDEX
    Explanations

    man, woman, couple, friend

    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
    æĭľå¸Ī
    -0.10
    ç½ħ
    -0.10
    èĹķ
    -0.09
    æĬĬèĩªå·±çļĦ
    -0.09
    请çĤ¹åĩ»
    -0.09
    imit
    -0.09
    éľľ
    -0.08
    åĵªå®¶
    -0.08
    å¦Ĩ
    -0.08
     Bra
    -0.08
    POSITIVE LOGITS
    åħ½
    0.09
    ether
    0.09
     ÑģÑĤо
    0.09
    ç¬ĶèĢħ
    0.09
    emble
    0.08
    åIJįçīĮ
    0.08
    çķĮ
    0.08
    åħµåĽ¢
    0.08
    å±Ģéķ¿
    0.08
    _Val
    0.08
    Activations Density 0.115%

    No Known Activations