© 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. 39091
    Prev
    Next
    INDEX
    Explanations

    exact details

    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
    åīįæīĢ
    -0.09
    ä¸įç®¡ä½ł
    -0.09
    åĩĮ
    -0.09
    æļĹ示
    -0.09
    _GENERIC
    -0.08
    èįĩ
    -0.08
    iquer
    -0.08
    _STANDARD
    -0.08
    _fb
    -0.08
    IQUE
    -0.08
    POSITIVE LOGITS
    åħ·ä½ĵ
    0.22
    åħ·ä½ĵçļĦ
    0.21
     exact
    0.18
    åħ·ä½ĵåĨħ容
    0.18
    çļĦåħ·ä½ĵ
    0.17
    exact
    0.15
    åħ·ä½ĵæĥħåĨµ
    0.13
    详ç»Ĩ
    0.13
     specifics
    0.13
    Exact
    0.12
    Activations Density 0.087%

    No Known Activations