© 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. 35779
    Prev
    Next
    INDEX
    Explanations

    bail, bale, ailed

    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
    aceous
    -0.10
    elves
    -0.10
     заÑīиÑĤÑĭ
    -0.10
    ally
    -0.09
    ality
    -0.09
    åĩĢåĮĸ
    -0.09
    ðŁ¤Ķ
    -0.09
     ТÑĥÑĢ
    -0.09
    credible
    -0.09
    éºĿ
    -0.08
    POSITIVE LOGITS
    bones
    0.10
    atory
    0.10
    ement
    0.09
    åĪ¶åº¦æĶ¹éĿ©
    0.09
    rooms
    0.09
    ernet
    0.09
    .optimizer
    0.08
     GOOGLE
    0.08
    ObjectContext
    0.08
    绡
    0.08
    Activations Density 0.003%

    No Known Activations