© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21011
    Prev
    Next
    INDEX
    Explanations

    modern

    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
    åŁ
    -0.10
    former
    -0.09
    æIJIJ
    -0.09
    лем
    -0.09
    nger
    -0.08
    æľªæĿ¥åıijå±ķ
    -0.08
    ited
    -0.08
    uted
    -0.08
    pees
    -0.08
    ared
    -0.08
    POSITIVE LOGITS
    -day
    0.16
    izing
    0.15
    ized
    0.15
    ize
    0.15
    ization
    0.15
    izr
    0.14
    mente
    0.13
    izer
    0.13
    idad
    0.13
    -minded
    0.12
    Activations Density 0.017%

    No Known Activations