© 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. 57708
    Prev
    Next
    INDEX
    Explanations

    phase II, phased out, phase transition

    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
    Ñĩик
    -0.11
    éĺ¶å±Ĥ
    -0.11
    ÑĩаÑģ
    -0.11
    èĬ±å¼Ģ
    -0.09
    istic
    -0.09
    entes
    -0.09
    ted
    -0.09
    iger
    -0.09
    ег
    -0.09
    insic
    -0.08
    POSITIVE LOGITS
    hift
    0.13
    ëģĶ
    0.12
    ë³Ħ
    0.10
    ONTAL
    0.10
    ioned
    0.10
    æĽĻ
    0.10
    bite
    0.10
    éĿ¢ä¸Ĭ
    0.09
    icularly
    0.09
    itur
    0.09
    Activations Density 0.045%

    No Known Activations