© 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. 50359
    Prev
    Next
    INDEX
    Explanations

    force of, force continuum, forceful

    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
    æľįåĬ¡è´¨éĩı
    -0.11
    ry
    -0.10
    èĭ¦æģ¼
    -0.09
     Wolff
    -0.08
    ãĤº
    -0.08
    ialog
    -0.08
    ues
    -0.08
    丰å¯Įå¤ļ彩
    -0.08
    rz
    -0.08
    å®īåħ¨ä¿Ŀéļľ
    -0.08
    POSITIVE LOGITS
    ful
    0.15
    fully
    0.14
    lessly
    0.11
    fulness
    0.11
    less
    0.11
    able
    0.11
    lessness
    0.10
     mẽ
    0.10
    FUL
    0.09
    hold
    0.09
    Activations Density 0.024%

    No Known Activations