© 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. 63041
    Prev
    Next
    INDEX
    Explanations

    hunting, sporting, firearms

    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
    ä»Ģä¹Īéĥ½
    -0.10
    éģĹçķĻ
    -0.10
    izr
    -0.09
    äºī缸
    -0.09
    ahoo
    -0.09
    馥
    -0.09
    Č
    -0.09
     bil
    -0.08
     coco
    -0.08
    ç
    -0.08
    POSITIVE LOGITS
    毡
    0.10
    éĽī
    0.09
     preamble
    0.09
    ç»Ī端
    0.09
    溯
    0.08
    éĢĤ
    0.08
    ç¾½æ¯ĽçIJĥ
    0.08
    ׾×Ķ
    0.08
    овÑĭÑħ
    0.08
    عاد
    0.08
    Activations Density 0.150%

    No Known Activations