© 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. 63040
    Prev
    Next
    INDEX
    Explanations

    Raj names and suffixes

    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
    еÑĢе
    -0.10
    çĦ¶æĺ¯
    -0.10
    IBLE
    -0.09
    ought
    -0.09
    essler
    -0.09
    wis
    -0.09
    èĶļ
    -0.09
    icks
    -0.09
    åĮ®
    -0.09
    å¤ł
    -0.08
    POSITIVE LOGITS
    SES
    0.10
    ruptcy
    0.09
    istic
    0.09
    istrate
    0.09
    æŀķ
    0.09
    çĸĹ
    0.09
    stro
    0.08
    illon
    0.08
    æľŁéĹ´
    0.08
    ıkl
    0.08
    Activations Density 0.019%

    No Known Activations