© 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. 2876
    Prev
    Next
    INDEX
    Explanations

    shipping and handling cost

    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
    ä»°
    -0.09
    èµ·çĤ¹
    -0.09
    çĦ¦çĤ¹
    -0.09
    åŃĿ
    -0.09
     reimb
    -0.09
    PrototypeOf
    -0.09
    å¢ĥ
    -0.09
    icide
    -0.09
    æ´¾
    -0.08
    æĪ·
    -0.08
    POSITIVE LOGITS
    è´¹
    0.15
    è²»
    0.14
    ä¸Ģ项
    0.11
    è´¹çĶ¨
    0.10
    æĪIJæľ¬
    0.10
    åĢ¬
    0.10
    ä¸ĢéĹ´
    0.10
    ivec
    0.09
    ftime
    0.09
    _COST
    0.09
    Activations Density 0.073%

    No Known Activations