© 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. 31085
    Prev
    Next
    INDEX
    Explanations

    what do you think

    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
     somew
    -0.09
    对å¤ĸ
    -0.09
    æŀ
    -0.09
    èĽŃ
    -0.09
    bum
    -0.09
    agus
    -0.08
    -gnu
    -0.08
    ỡ
    -0.08
    iring
    -0.08
    èĭ
    -0.08
    POSITIVE LOGITS
    nej
    0.09
    ä¿ı
    0.09
    æł·åŃIJ
    0.09
    bras
    0.09
    ems
    0.08
    rams
    0.08
    atest
    0.08
     mej
    0.08
    åĤ¬çĶŁ
    0.08
     advoc
    0.08
    Activations Density 0.010%

    No Known Activations