© 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. 4082
    Prev
    Next
    INDEX
    Explanations

    sale to

    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
    ils
    -0.10
    å¹´é¾Ħ段
    -0.09
    2
    -0.08
    ç¡ķ
    -0.08
    æľ¬éĩij
    -0.08
    4
    -0.08
    3
    -0.08
    udos
    -0.08
    1
    -0.07
    7
    -0.07
    POSITIVE LOGITS
    éªŀ
    0.11
    éĺ¶
    0.10
    AnimationFrame
    0.10
    åģ»
    0.10
    Entities
    0.10
    еле
    0.09
    第ä¸īæĸ¹
    0.09
    诸å¦Ĥ
    0.09
     BaseEntity
    0.09
    gee
    0.09
    Activations Density 0.035%

    No Known Activations