© 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. 36038
    Prev
    Next
    INDEX
    Explanations

    Carolina

    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
    åĦ¿å¥³
    -0.11
    çľģæĶ¿åºľ
    -0.10
    ç±³å°Ķ
    -0.10
    หมาย
    -0.10
    dom
    -0.10
    伪éĢł
    -0.09
    çĹĩ
    -0.09
    è¨Ĺ
    -0.09
    dist
    -0.09
    ural
    -0.09
    POSITIVE LOGITS
    oor
    0.10
    bö
    0.09
    iates
    0.09
    alley
    0.09
    ergic
    0.08
    ä¿©
    0.08
    eres
    0.08
    aan
    0.08
     Ñģебе
    0.08
    añ
    0.08
    Activations Density 0.018%

    No Known Activations