© 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. 5137
    Prev
    Next
    INDEX
    Explanations

    Los Angeles Times

    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
    bles
    -0.09
    IMUM
    -0.09
    æŀĭ
    -0.08
     hug
    -0.08
     paren
    -0.08
    adoo
    -0.08
    iginal
    -0.08
    LER
    -0.07
    boom
    -0.07
    Ñģл
    -0.07
    POSITIVE LOGITS
    PropertyParams
    0.12
    gne
    0.10
    æIJŀ好
    0.10
    èĭ£
    0.10
    漪
    0.09
    å¾Ń
    0.09
    é«»
    0.09
    åıĺå¼Ĥ
    0.09
    íĮIJ
    0.09
    OptionsResolver
    0.09
    Activations Density 0.002%

    No Known Activations