© 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. 21759
    Prev
    Next
    INDEX
    Explanations

    competencies, learning, research, literature, workforce

    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
    æīĺ
    -0.10
    çĦķ
    -0.09
     Prel
    -0.09
    atha
    -0.09
    thalm
    -0.09
    èı©
    -0.09
    ido
    -0.08
    èĤļ
    -0.08
    Licensed
    -0.08
    康å¤į
    -0.08
    POSITIVE LOGITS
    ubern
    0.09
    æī£
    0.08
    æ¯ĶèµĽä¸Ń
    0.08
    Bug
    0.08
    çīĿ
    0.08
    quer
    0.08
    èĸª
    0.08
    帽
    0.08
    à¹Īาย
    0.08
    embr
    0.08
    Activations Density 0.599%

    No Known Activations