© 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. 57931
    Prev
    Next
    INDEX
    Explanations

    st words ending in 'ool', 'ore', 'ell'

    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
    ster
    -0.10
    ãģĵãģĿ
    -0.10
    åı²ä¸Ĭ
    -0.09
    ohn
    -0.09
    -scalable
    -0.09
    (es
    -0.09
    er
    -0.09
    ìĦĿ
    -0.09
    ä¸ĸ家
    -0.08
    ç¬Ļ
    -0.08
    POSITIVE LOGITS
    ä¸Ģè´¯
    0.12
    illing
    0.11
    é£ŀæī¬
    0.10
    wich
    0.09
    imming
    0.09
    ä¸Ģçĵ¶
    0.09
    åĿ¦
    0.09
    è¯Ŀ
    0.09
    çĦķåıij
    0.08
    ä¸ĢæĿ¡é¾Ļ
    0.08
    Activations Density 0.237%

    No Known Activations