© 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. 34448
    Prev
    Next
    INDEX
    Explanations

    items in lists

    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
    Boss
    -0.09
    @brief
    -0.08
     Ones
    -0.08
    apy
    -0.08
    èĤ¤
    -0.08
    boss
    -0.08
     descon
    -0.08
    ︱
    -0.08
    åĽ°æĥij
    -0.08
    roker
    -0.08
    POSITIVE LOGITS
    éĻĦè¿ij
    0.13
    éĻĦè¿ijçļĦ
    0.12
    æīĢåľ¨åľ°
    0.10
    åĿIJèIJ½åľ¨
    0.10
    åĪĨå¸ĥåľ¨
    0.09
    çĶ¨åľ°
    0.09
     nearby
    0.09
    ä¸įè¿ľå¤Ħ
    0.09
     notable
    0.09
    è´¯
    0.09
    Activations Density 0.075%

    No Known Activations