© 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. 58810
    Prev
    Next
    INDEX
    Explanations

    childhood and its 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
    å¹´è½»çļĦ
    -0.10
    åı¯æĥľ
    -0.09
    ç©ij
    -0.09
    人å¿ĥ
    -0.09
    ings
    -0.09
    æĪĸå¤ļ
    -0.09
    eyed
    -0.09
    ets
    -0.08
    ìĺ¬
    -0.08
    eds
    -0.08
    POSITIVE LOGITS
    ishly
    0.11
    sWith
    0.10
    ç§įç§į
    0.09
    akk
    0.09
    agne
    0.09
    ebin
    0.09
    迹象
    0.09
    valuate
    0.09
    ern
    0.09
    çĶ¨åĵģ
    0.09
    Activations Density 0.011%

    No Known Activations