© 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. 56450
    Prev
    Next
    INDEX
    Explanations

    christmas lights, tree, season, story, card

    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
    lessly
    -0.10
    ìĤ¬íķŃ
    -0.10
    ings
    -0.10
    æĥĭ
    -0.10
    spath
    -0.10
    inders
    -0.09
    亢
    -0.09
    æŃī
    -0.09
    çķĶ
    -0.09
    anst
    -0.09
    POSITIVE LOGITS
    -themed
    0.10
    iani
    0.10
    /Linux
    0.09
    tin
    0.09
    çĶ¨åĵģ
    0.09
    å®ĺåı¸
    0.08
    ìĥī
    0.08
     Hayes
    0.08
    vero
    0.08
    -coded
    0.08
    Activations Density 0.006%

    No Known Activations