© 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. 10902
    Prev
    Next
    INDEX
    Explanations

    you under

    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
    æĿ¥èĩª
    -0.12
    æıĨ
    -0.10
    æĶ¾åĪ°
    -0.10
    æĿ¥åĪ°
    -0.09
    stad
    -0.09
    åĪ°è¿ĻéĩĮ
    -0.09
    stp
    -0.09
    çĶ¨æĿ¥
    -0.09
    è¿ĻéĩĮ
    -0.09
    æľĿçĿĢ
    -0.09
    POSITIVE LOGITS
    为æŃ¢
    0.18
     detriment
    0.16
    缮åīį为æŃ¢
    0.15
     liking
    0.13
    /from
    0.13
    gether
    0.12
     extent
    0.12
    tems
    0.12
     fullest
    0.11
    æ·±å¤Ħ
    0.11
    Activations Density 0.831%

    No Known Activations