© 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. 62876
    Prev
    Next
    INDEX
    Explanations

    kissing or kissed

    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
    ç¾İå¾·
    -0.09
    享åıĹ
    -0.08
    illet
    -0.08
    vang
    -0.08
    etail
    -0.08
    ¢
    -0.08
    ève
    -0.08
    .fin
    -0.08
    ordin
    -0.08
    asm
    -0.08
    POSITIVE LOGITS
    emma
    0.10
    èĮĨ
    0.09
    abra
    0.09
    è¡ĵ
    0.09
    _notifier
    0.09
     далÑĮ
    0.09
    è³¼çī©
    0.09
    Ñģел
    0.09
    åł
    0.09
    :result
    0.09
    Activations Density 0.006%

    No Known Activations