© 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. 36217
    Prev
    Next
    INDEX
    Explanations

    above copyright notice

    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
    ambi
    -0.10
    ย
    -0.10
    /renderer
    -0.09
    ä¸įå¦Ĥ
    -0.09
    ä¸ĭåİ»
    -0.09
    atura
    -0.09
    adge
    -0.09
    åīĸ
    -0.09
    媳
    -0.09
    ä¸ĭä¸Ģ代
    -0.09
    POSITIVE LOGITS
    çĺ¾
    0.13
    ðŁijĨ
    0.11
    岸
    0.11
    -described
    0.10
    above
    0.09
    ech
    0.09
    -dess
    0.09
    佬
    0.09
    head
    0.09
    ground
    0.09
    Activations Density 0.081%

    No Known Activations