© 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. 30955
    Prev
    Next
    INDEX
    Explanations

    HTML DOCTYPE

    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
    æŃĥ
    -0.10
    æĪIJçĨŁ
    -0.10
    èľķ
    -0.09
    oblin
    -0.09
    acular
    -0.09
    éĺī
    -0.09
    è¯ĬæīĢ
    -0.09
    Ñģан
    -0.08
     chees
    -0.08
    otal
    -0.08
    POSITIVE LOGITS
    æķijåĬ©
    0.10
    ç¼Ĩ
    0.10
    éģĩéļ¾
    0.10
    æķij
    0.09
    èĪ¹ä¸Ĭ
    0.09
     Surv
    0.09
     Titanic
    0.09
    uite
    0.09
    çĶŁæŃ»
    0.09
    æĢ§åij½
    0.09
    Activations Density 0.032%

    No Known Activations