© 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. 17104
    Prev
    Next
    INDEX
    Explanations

    having trouble/difficulty

    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
    çŀ»
    -0.10
    .ga
    -0.09
    hel
    -0.09
    helm
    -0.09
    å½Ģ
    -0.08
    人人
    -0.08
    \Abstract
    -0.08
    令
    -0.08
    REEN
    -0.08
     Little
    -0.08
    POSITIVE LOGITS
    缴æݥ影åĵį
    0.09
    åĩī
    0.09
     trouble
    0.09
    æĶ¶ç¼©
    0.09
    æĿ°
    0.09
    ä¿İ
    0.08
    ä¸ĭ鼨
    0.08
    æĪĸå°Ĩ
    0.08
    onta
    0.08
    丰æĶ¶
    0.08
    Activations Density 0.026%

    No Known Activations