© 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. 35772
    Prev
    Next
    INDEX
    Explanations

    microorganisms, microprocessors, microbial, microRNA

    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
     dolayı
    -0.10
    /OR
    -0.10
    ement
    -0.10
    ned
    -0.10
    æ¡İ
    -0.10
    æ»ĵ
    -0.09
     thù
    -0.09
    ays
    -0.09
    mir
    -0.09
    aying
    -0.09
    POSITIVE LOGITS
    -minded
    0.13
    angelo
    0.12
     minded
    0.12
    loth
    0.11
    bial
    0.10
    icult
    0.09
    hood
    0.09
    ãĥ£
    0.09
    ature
    0.09
    ellaneous
    0.09
    Activations Density 0.104%

    No Known Activations