© 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. 49309
    Prev
    Next
    INDEX
    Explanations

    Yorkshire places and names

    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
    ogg
    -0.09
    lessly
    -0.09
    inding
    -0.08
    ê¹IJ
    -0.08
    ernational
    -0.08
    unce
    -0.08
    folios
    -0.08
    çĴŀ
    -0.08
    ä½ľèĢħæīĢæľī
    -0.08
    rub
    -0.08
    POSITIVE LOGITS
    izer
    0.11
    åIJİèĢħ
    0.09
    ialog
    0.09
    esis
    0.09
    beck
    0.09
    åı°éĺ¶
    0.08
    åIJĮç±»
    0.08
    åıĺæĢģ
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
     pains
    0.08
    Activations Density 0.003%

    No Known Activations