© 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. 984
    Prev
    Next
    INDEX
    Explanations

    Netherlands

    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
    ðŁı»
    -0.12
    ë§IJ
    -0.10
    elper
    -0.10
    ä¸ŃåĽ½åĽ½éĻħ
    -0.10
    opia
    -0.09
    ties
    -0.09
    ðŁı½
    -0.09
    çĽī
    -0.09
    зв
    -0.09
    ernel
    -0.09
    POSITIVE LOGITS
    hip
    0.10
    ucas
    0.09
    Į
    0.09
    oder
    0.09
    atical
    0.09
    isos
    0.08
    zik
    0.08
    æµ·å²Ľ
    0.08
    å¹³åĿ¦
    0.08
    atic
    0.08
    Activations Density 0.010%

    No Known Activations