© 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. 10120
    Prev
    Next
    INDEX
    Explanations

    sexual behavior and content

    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
    å¹ħ
    -0.09
    åĶĨ
    -0.08
     nghá»ģ
    -0.08
    è¶Ĭ好
    -0.08
    åį³ä½¿æĺ¯
    -0.08
    ilo
    -0.08
     Ñģозда
    -0.08
    uffer
    -0.08
     Ether
    -0.08
    ä»·
    -0.08
    POSITIVE LOGITS
    ized
    0.13
    нÑĮ
    0.12
    aight
    0.10
    idan
    0.09
    åĮĸçļĦ
    0.09
    деÑģÑıÑĤ
    0.08
    marvin
    0.08
    iteit
    0.08
    izing
    0.08
    ../../
    0.08
    Activations Density 0.027%

    No Known Activations