© 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. 12029
    Prev
    Next
    INDEX
    Explanations

    gaming

    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
    ope
    -0.11
     Ñģобой
    -0.10
    EVER
    -0.09
    backs
    -0.09
    generation
    -0.09
    ÑĨеп
    -0.08
    ings
    -0.08
    ×ķת
    -0.08
    ru
    -0.08
    cial
    -0.08
    POSITIVE LOGITS
    amp
    0.13
    ãĥ£
    0.09
    æĺĶ
    0.09
    ye
    0.09
    ÙĬÙĪÙĨ
    0.09
    æѤåĪ»
    0.09
    -grade
    0.09
    ying
    0.09
    éªħ
    0.09
    åľ°åĿª
    0.08
    Activations Density 0.026%

    No Known Activations