© 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. 34709
    Prev
    Next
    INDEX
    Explanations

    have/has been

    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
    pson
    -0.11
    æĻ¦
    -0.10
    ä¸Ģæŀ¶
    -0.10
     mop
    -0.10
    elas
    -0.09
    缼è¡Į
    -0.09
    çĸ²æĥ«
    -0.09
    èĬľ
    -0.09
    ä¸Ģéģį
    -0.08
    äºĮæīĭ
    -0.08
    POSITIVE LOGITS
     Conserv
    0.10
    esa
    0.10
    åĭ¾
    0.10
    该æĢİä¹ĪåĬŀ
    0.09
    ionate
    0.08
    åŁºç¡Ģ
    0.08
    amd
    0.08
    gh
    0.08
    åŁºç¤İ
    0.08
     Lal
    0.08
    Activations Density 0.137%

    No Known Activations