© 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. 22492
    Prev
    Next
    INDEX
    Explanations

    this

    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
    objs
    -0.10
    åĩ«
    -0.10
     напÑĢавлен
    -0.09
    çģ¶
    -0.09
    æĨĶ
    -0.09
    _MATERIAL
    -0.08
    澧
    -0.08
    èĦ¸éĥ¨
    -0.08
    åľ¬
    -0.08
    aura
    -0.08
    POSITIVE LOGITS
    æĢĿèĢĥ
    0.16
    æĢĿç´¢
    0.15
    çIJ¢ç£¨
    0.14
    æĥ³äºĨæĥ³
    0.13
    èĢĥèĻij
    0.13
    æĸŁ
    0.12
     thought
    0.11
    ä»Ķç»Ĩ
    0.11
    åħ¬åħ±åľºæīĢ
    0.11
    æĥ³æĥ³
    0.10
    Activations Density 0.040%

    No Known Activations