© 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. 56347
    Prev
    Next
    INDEX
    Explanations

    hundreds of

    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
    Ñħодим
    -0.10
    er
    -0.10
    ÑĤив
    -0.09
    ../
    -0.09
    <<<<<<<<
    -0.09
    åĻĹ
    -0.09
    istory
    -0.09
    bam
    -0.09
    oru
    -0.09
    Hierarchy
    -0.09
    POSITIVE LOGITS
     dozen
    0.11
    ä¸Ĭåįĥ
    0.11
    że
    0.10
    ric
    0.10
     ngÃłn
    0.09
     nghìn
    0.09
     thousand
    0.09
    archical
    0.09
    ween
    0.09
    åĿļæĮģä¸įæĩĪ
    0.08
    Activations Density 0.025%

    No Known Activations