© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38069
    Prev
    Next
    INDEX
    Explanations

    snap shots

    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
    ØŃر
    -0.10
    å¯Ħæīĺ
    -0.10
    ritt
    -0.09
    家çĶµ
    -0.09
    å½Ģ
    -0.09
    亡
    -0.08
    verages
    -0.08
    ä¸ĢæŃ¥æŃ¥
    -0.08
     novelty
    -0.08
    çĶļ
    -0.08
    POSITIVE LOGITS
    主ä¸ļ
    0.10
    shots
    0.10
    ÑĩаÑĤ
    0.10
    cribe
    0.09
    oola
    0.09
    flow
    0.09
    PEAR
    0.09
    stone
    0.09
    ning
    0.09
    ieties
    0.09
    Activations Density 0.008%

    No Known Activations