© 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. 51281
    Prev
    Next
    INDEX
    Explanations

    military personnel and charities

    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
    atus
    -0.09
    ç¨Ģ
    -0.09
    bos
    -0.09
    irates
    -0.08
    æĿ¡çº¦
    -0.08
    åIJ¹
    -0.08
    obili
    -0.08
    åħļæĢ»
    -0.08
     Trails
    -0.08
    æĹ¥å¸¸
    -0.08
    POSITIVE LOGITS
    æħ°éĹ®
    0.11
    æħ°
    0.10
     morale
    0.09
     conj
    0.09
     POW
    0.09
    è¿Ķ乡
    0.09
    件
    0.09
    麸
    0.09
    ParameterValue
    0.08
    æ¯ĶåĪ©
    0.08
    Activations Density 0.069%

    No Known Activations