© 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. 2663
    Prev
    Next
    INDEX
    Explanations

    cout << "..."

    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
    è¾ĺ
    -0.10
    强大çļĦ
    -0.09
    enny
    -0.08
    arium
    -0.08
    èĭ¹
    -0.08
    ody
    -0.08
    强大
    -0.08
    è½Ń
    -0.08
    åħīèį£
    -0.08
    pla
    -0.08
    POSITIVE LOGITS
    æĿ¥çĶµ
    0.10
    éĢł
    0.10
    ety
    0.09
    è¿Ļæł·æīįèĥ½
    0.09
    è¹²
    0.08
    èĸ®
    0.08
    æĶ¾å¿ĥ
    0.08
    unik
    0.08
    glomer
    0.08
    ä¹ŁæŃ£æĺ¯
    0.08
    Activations Density 0.004%

    No Known Activations