© 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. 10535
    Prev
    Next
    INDEX
    Explanations

    noise level

    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
    å£°éŁ³
    -0.14
    åĻªéŁ³
    -0.13
    åĻªå£°
    -0.11
    èģ²éŁ³
    -0.10
    çļĦå£°éŁ³
    -0.10
    æ°Ķåij³
    -0.10
     sound
    -0.09
     noise
    -0.09
    èIJ¤
    -0.09
    неÑĨ
    -0.09
    POSITIVE LOGITS
    æĸĹ
    0.09
    Ãłn
    0.09
     gent
    0.08
    ен
    0.08
     ImVec
    0.08
    (Xml
    0.08
    ÑĢоÑģ
    0.08
    ком
    0.07
    çĶ¨èį¯
    0.07
     Harper
    0.07
    Activations Density 0.034%

    No Known Activations