© 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. 9699
    Prev
    Next
    INDEX
    Explanations

    dimensions

    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
    ä¼ı
    -0.10
    orte
    -0.08
    nt
    -0.08
    ulp
    -0.08
     hero
    -0.08
    åĽł
    -0.08
    ks
    -0.08
    s
    -0.08
    åŃ©
    -0.08
    éĢı
    -0.08
    POSITIVE LOGITS
    /OR
    0.11
    ä»Ģä¹Īåij¢
    0.10
    ãģĿãģĨãģ§
    0.10
    岸
    0.10
    åĪ«çļĦ
    0.10
    Locker
    0.10
    ä»Ģä¹Īéĥ½ä¸į
    0.10
    xmm
    0.09
    大家åĪĨ享
    0.09
    -other
    0.09
    Activations Density 0.036%

    No Known Activations