© 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. 38707
    Prev
    Next
    INDEX
    Explanations

    exam, test, skills

    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
    oya
    -0.10
    åѦåijĺ
    -0.10
    éģĩéļ¾
    -0.10
    ogan
    -0.09
    vana
    -0.09
    Ľå»º
    -0.09
    åĺ´éĩĮ
    -0.09
    icip
    -0.09
    iar
    -0.08
     полÑĥ
    -0.08
    POSITIVE LOGITS
    è¿ĻäºĽä¸ľè¥¿
    0.09
     tests
    0.09
     test
    0.09
    skills
    0.09
    4
    0.08
    æĸ¹å¼ıè¿Ľè¡Į
    0.08
    æĻºèĥ½åĪ¶éĢł
    0.08
     duck
    0.08
    缸åħ³åĨħ容
    0.08
     skills
    0.08
    Activations Density 0.047%

    No Known Activations