© 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. 3171
    Prev
    Next
    INDEX
    Explanations

    submitted once

    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¿Ŀé²ľ
    -0.09
    ç¿ĺ
    -0.09
     ÑģовеÑĢÑĪен
    -0.09
    æīģ
    -0.09
    mites
    -0.09
    LOCKS
    -0.09
     Gaul
    -0.09
     Bride
    -0.09
    _border
    -0.08
    agara
    -0.08
    POSITIVE LOGITS
    书éĿ¢
    0.11
    é¦ĸåħĪè¦ģ
    0.10
    å°±è¿ij
    0.09
    ouch
    0.09
    æݩ饰
    0.08
    Jet
    0.08
    ove
    0.08
    -maker
    0.08
    å¿ħé¡»
    0.08
    åIJij
    0.08
    Activations Density 0.030%

    No Known Activations