© 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. 35336
    Prev
    Next
    INDEX
    Explanations

    Argentina

    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
    apter
    -0.10
    RAR
    -0.09
    书åºĹ
    -0.09
    inci
    -0.09
    åľ»
    -0.09
    oftware
    -0.09
    ะ
    -0.09
    LastError
    -0.08
     shalt
    -0.08
    æµĻæ±Łçľģ
    -0.08
    POSITIVE LOGITS
     Mafia
    0.10
    佬
    0.10
    entina
    0.10
    ised
    0.09
    eous
    0.09
    nie
    0.09
    onaut
    0.09
    è²Į
    0.09
    uation
    0.09
    é£İåij³
    0.09
    Activations Density 0.021%

    No Known Activations