© 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. 39308
    Prev
    Next
    INDEX
    Explanations

    singular or peculiar endings

    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
    SES
    -0.08
    side
    -0.08
     flo
    -0.08
    çºł
    -0.08
     Äijỡ
    -0.08
    esh
    -0.08
    ìĦľ
    -0.08
    èijº
    -0.08
    artment
    -0.08
    lean
    -0.08
    POSITIVE LOGITS
    ities
    0.20
    ly
    0.15
    mente
    0.13
    ITIES
    0.13
    thur
    0.12
    ously
    0.10
    idade
    0.10
    tons
    0.10
    ists
    0.09
    ize
    0.09
    Activations Density 0.008%

    No Known Activations