© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9407
    Prev
    Next
    INDEX
    Explanations

    running out

    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
    acro
    -0.09
    æĿĤçī©
    -0.08
    åħļçļĦé¢Ĩ导
    -0.08
     плоÑĤ
    -0.08
     encrypted
    -0.08
    åĽ´çĿĢ
    -0.08
    ëį´
    -0.08
    æ§Ł
    -0.08
    dens
    -0.08
    æĪIJç«ĭäºİ
    -0.08
    POSITIVE LOGITS
     exhausted
    0.15
    èĢĹ
    0.14
     exhaustion
    0.14
     Exhaust
    0.14
     depletion
    0.12
    æ¶ĪèĢĹ
    0.12
     depleted
    0.11
    涸
    0.11
     exhausting
    0.10
     exhaust
    0.10
    Activations Density 0.089%

    No Known Activations