© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52755
    Prev
    Next
    INDEX
    Explanations

    hype and fuss

    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
    æķŀ
    -0.09
    éĶ»çĤ¼
    -0.08
    æŃª
    -0.08
    ì¦Ŀ
    -0.08
    åľ°éģĵ
    -0.08
     Forrest
    -0.08
    å§ĵ
    -0.08
    pps
    -0.08
    bt
    -0.08
    opro
    -0.08
    POSITIVE LOGITS
     hype
    0.11
    å¤¸å¼ł
    0.10
    åªĴä½ĵ
    0.10
    äºĨåįĬ天
    0.09
     fuss
    0.09
    çijĹ
    0.09
    渲æŁĵ
    0.09
    åĺĺ
    0.09
    ä¸ĢæŶ
    0.09
    untu
    0.09
    Activations Density 0.072%

    No Known Activations