© 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. 19595
    Prev
    Next
    INDEX
    Explanations

    candidate / contender

    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
    éŀŃ
    -0.11
    .foundation
    -0.10
    ä¸ĢåĪĢ
    -0.10
    åħģ许
    -0.09
    è¦Ĩ
    -0.09
    олÑĮз
    -0.09
    ä¸įåħģ许
    -0.08
    碣
    -0.08
     Merchant
    -0.08
    riz
    -0.08
    POSITIVE LOGITS
    åĢĻéĢī
    0.29
    åĢĻéĢī人
    0.24
     candidates
    0.23
     candidate
    0.21
    å«Įçĸij
    0.19
     Candidates
    0.19
    candidates
    0.19
    candidate
    0.18
     contenders
    0.18
    Candidates
    0.18
    Activations Density 0.141%

    No Known Activations