© 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. 59026
    Prev
    Next
    INDEX
    Explanations

    berry or strawberry

    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
    erval
    -0.10
    sic
    -0.09
    ãģĹãģ¾ãģĨ
    -0.09
    æ¡ħ
    -0.09
    enance
    -0.09
    ité
    -0.09
    arb
    -0.09
    bourne
    -0.08
    ila
    -0.08
    ä¿Ŀåħ»
    -0.08
    POSITIVE LOGITS
    è¹ĭ
    0.11
    stalk
    0.11
    keit
    0.11
    pedia
    0.09
    à¥įà¤
    0.09
    halb
    0.09
    íĬ¼
    0.09
    onda
    0.09
    anno
    0.09
    طا
    0.09
    Activations Density 0.013%

    No Known Activations