© 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. 48150
    Prev
    Next
    INDEX
    Explanations

    copies of

    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
    ancia
    -0.10
    çļĦæĥħ
    -0.10
    çĶ¨åĵģ
    -0.09
    ly
    -0.09
    amp
    -0.09
     nostr
    -0.09
    esse
    -0.09
    -child
    -0.09
    yr
    -0.08
    âĸĪ
    -0.08
    POSITIVE LOGITS
    .deepcopy
    0.16
    writing
    0.11
    ees
    0.11
    tures
    0.11
    ABLE
    0.10
    æİĩ
    0.10
    volution
    0.10
    outs
    0.10
    RIGHT
    0.10
    注éĶĢ
    0.09
    Activations Density 0.068%

    No Known Activations