© 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. 5651
    Prev
    Next
    INDEX
    Explanations

    new followed by noun

    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
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.10
    ared
    -0.09
    ate
    -0.08
    éķĹ
    -0.08
    izar
    -0.08
    å®ĹæŨ
    -0.08
    æĻ®éģįåŃĺåľ¨
    -0.08
    åħ¶æ¬¡
    -0.08
     second
    -0.08
    åħ¶ä¸Ńä¸Ģ个
    -0.08
    POSITIVE LOGITS
    erties
    0.09
     ways
    0.09
    ëį°
    0.09
    /welcome
    0.08
    ISTER
    0.08
     avenues
    0.08
    åĺ²
    0.08
    enti
    0.08
    lie
    0.08
    ç»ıéªĮåĴĮ
    0.08
    Activations Density 0.042%

    No Known Activations