© 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. 34903
    Prev
    Next
    INDEX
    Explanations

    whole noun phrase

    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
    人æķ°
    -0.09
    é»ij马
    -0.09
    延
    -0.09
    Å«
    -0.08
     ниÑĩ
    -0.08
    POS
    -0.08
    æĬĬè¿ĻäºĽ
    -0.08
    人éĹ´
    -0.08
    çļĦèĦļæŃ¥
    -0.08
    窦
    -0.08
    POSITIVE LOGITS
    irsch
    0.10
    äºĭåĦ¿
    0.10
    iance
    0.10
    侦
    0.09
    terior
    0.09
    ILLS
    0.09
    æ®ĵ
    0.09
    å±ĢéĿ¢
    0.09
     Bath
    0.09
    iliation
    0.08
    Activations Density 0.016%

    No Known Activations