© 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. 50402
    Prev
    Next
    INDEX
    Explanations

    animation and animate

    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
    æ»ĭ
    -0.09
    ivers
    -0.09
    缸çĪ±
    -0.09
    ãĥĢãĥ¼
    -0.08
    æĺİæĻ°
    -0.08
    ç¶ļ
    -0.08
    俸
    -0.08
     Lik
    -0.08
    NonNull
    -0.08
    ä»ĺ
    -0.08
    POSITIVE LOGITS
    /animations
    0.11
    jin
    0.10
    èĢ»
    0.10
    æ®ĭ
    0.10
    /animate
    0.10
    .animation
    0.09
    åĬ¨çĶ»
    0.09
    æ®ĺ
    0.09
    å¹ħ度
    0.09
    atable
    0.09
    Activations Density 0.110%

    No Known Activations