© 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. 37570
    Prev
    Next
    INDEX
    Explanations

    Dover Rug & Home

    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
    çĪª
    -0.10
    мел
    -0.10
    riba
    -0.09
    çľī
    -0.09
     eventual
    -0.09
    CLUD
    -0.09
    澡
    -0.09
    marshall
    -0.09
    inci
    -0.09
     Disco
    -0.09
    POSITIVE LOGITS
    ses
    0.10
    systems
    0.09
    ðŁı»
    0.09
    vince
    0.09
    uments
    0.08
     Kimber
    0.08
    æĺ¶
    0.08
    eref
    0.08
    æĢ»å±Ģ
    0.08
     eslint
    0.08
    Activations Density 0.002%

    No Known Activations