© 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. 32056
    Prev
    Next
    INDEX
    Explanations

    visual effects and transitions

    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
    ä¾ĽåĽ¾
    -0.09
    åıĸ代
    -0.09
    æ£ĭ
    -0.08
    æijĦ
    -0.08
    ä¿ĿæĮģçĿĢ
    -0.08
    紧紧
    -0.08
    emble
    -0.08
    è¡®
    -0.08
    éĥ
    -0.08
    пÑĢÑı
    -0.08
    POSITIVE LOGITS
    æķĪæŀľ
    0.25
    çļĦæķĪæŀľ
    0.19
     effect
    0.16
    effect
    0.15
     effects
    0.15
    Effect
    0.15
     Effect
    0.15
     ÑįÑĦÑĦ
    0.14
    .effect
    0.14
    -effect
    0.14
    Activations Density 0.079%

    No Known Activations