© 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. 9897
    Prev
    Next
    INDEX
    Explanations

    orcist

    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
    èij
    -0.10
    ÑĪка
    -0.09
    åıªè¦ģæľī
    -0.09
    lector
    -0.09
    人æ°ij群ä¼Ĺ
    -0.09
    é¹Į
    -0.09
    xor
    -0.08
    çļĦä¸ĢéĿ¢
    -0.08
    ÑĢад
    -0.08
    ftp
    -0.08
    POSITIVE LOGITS
    defer
    0.08
    æ¼ĵ
    0.08
    onacci
    0.08
    æ¥Ķ
    0.08
    ä¹ħäºĨ
    0.08
    NF
    0.08
    åı©
    0.08
    itol
    0.08
    è¦ĥ
    0.07
    tight
    0.07
    Activations Density 0.004%

    No Known Activations