© 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. 11037
    Prev
    Next
    INDEX
    Explanations

    budget cuts

    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
    å°ı康
    -0.10
    ä¸įä¸Ĭ
    -0.10
    urate
    -0.10
    WithOptions
    -0.10
    emento
    -0.09
    åı¬
    -0.09
    sig
    -0.09
    OrDefault
    -0.09
    ersen
    -0.09
    å¾ģæĶ¶
    -0.09
    POSITIVE LOGITS
    å¹ħ度
    0.12
    èĻ¢
    0.10
    PNG
    0.08
    éļIJæĤ£
    0.08
    è¾Ľè¾£
    0.08
    åħ®
    0.08
    åĬĽåº¦
    0.08
    æݪæĸ½
    0.08
    åIJİçļĦ
    0.08
    èĩ³æѤ
    0.08
    Activations Density 0.014%

    No Known Activations