© 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. 19933
    Prev
    Next
    INDEX
    Explanations

    attributing statements after quotes

    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
    ت
    -0.12
    ness
    -0.12
    tn
    -0.11
     ÑĢанее
    -0.10
    averse
    -0.10
     originally
    -0.10
    ãģĦãģŁãĤī
    -0.10
    ate
    -0.10
    emo
    -0.09
    è¦ģåİ»
    -0.09
    POSITIVE LOGITS
    ãĤĪãģĨãģ«ãģªãģ£ãģŁ
    0.11
    INGS
    0.10
    ings
    0.09
    /source
    0.09
    ingly
    0.09
    ervo
    0.09
    cheme
    0.09
    ä¹Ķ
    0.08
    eds
    0.08
    dney
    0.08
    Activations Density 0.040%

    No Known Activations