© 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. 37595
    Prev
    Next
    INDEX
    Explanations

    occurrences and their context

    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
    rock
    -0.11
    elt
    -0.11
    çħ¦
    -0.10
    esses
    -0.10
    krit
    -0.09
    è¿ĩ硬
    -0.09
    ãĤ
    -0.09
    zer
    -0.09
    buffers
    -0.09
    combe
    -0.09
    POSITIVE LOGITS
    ment
    0.10
    uate
    0.10
     ÑģоÑģÑĤ
    0.09
    äºĨä¸Ģ
    0.09
    äºĨä¸Ģ个
    0.09
    ant
    0.09
     xuyên
    0.09
    mediately
    0.09
    ally
    0.09
    nel
    0.09
    Activations Density 0.052%

    No Known Activations