© 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. 2626
    Prev
    Next
    INDEX
    Explanations

    seconds duration or rate

    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
    ãģ£ãģįãĤĬ
    -0.10
    ä¼Ļ
    -0.10
    绥
    -0.09
    äºĽä»Ģä¹Ī
    -0.09
    обоÑĢоÑĤ
    -0.09
    shed
    -0.09
    ETING
    -0.09
    âĸ¹
    -0.09
    itat
    -0.09
    asured
    -0.09
    POSITIVE LOGITS
    ary
    0.10
    ARY
    0.09
    ably
    0.09
    -lived
    0.09
    aries
    0.09
    åĵ¥
    0.08
     ago
    0.08
    linger
    0.08
    ally
    0.08
    aire
    0.08
    Activations Density 0.041%

    No Known Activations