© 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. 61371
    Prev
    Next
    INDEX
    Explanations

    impending or pending events

    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
    ниÑĨÑĭ
    -0.10
    неÑĨ
    -0.09
    çĹĽçĤ¹
    -0.09
    æĥ®
    -0.09
    æĻ°
    -0.09
    uen
    -0.09
    -même
    -0.08
    æĦ¤
    -0.08
    Ñģко
    -0.08
    owl
    -0.08
    POSITIVE LOGITS
     doom
    0.14
    elope
    0.10
    gaard
    0.10
    æ²ĵ
    0.09
    å¥İ
    0.09
    erson
    0.09
    raid
    0.09
    ertiary
    0.08
     zwar
    0.08
    LOUR
    0.08
    Activations Density 0.003%

    No Known Activations