© 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. 32346
    Prev
    Next
    INDEX
    Explanations

    baby or babies

    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
    ively
    -0.13
    ings
    -0.11
    ible
    -0.11
    fully
    -0.11
    west
    -0.10
    天河
    -0.10
    ally
    -0.10
    ality
    -0.10
    <![
    -0.10
    ément
    -0.10
    POSITIVE LOGITS
    doll
    0.12
    çĸĻ
    0.11
    ëģĶ
    0.10
    olas
    0.09
    otas
    0.09
    lic
    0.09
    riages
    0.08
    æĿµ
    0.08
    omial
    0.08
    bones
    0.08
    Activations Density 0.019%

    No Known Activations