© 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. 32464
    Prev
    Next
    INDEX
    Explanations

    aboard vehicles and transport

    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
    èĨı
    -0.09
    æļ´é£İ
    -0.09
    æĥ³åİ»
    -0.09
     played
    -0.09
    管å§Ķä¼ļ
    -0.09
    çĥŁèĬ±
    -0.08
    ä¸İä¸ŃåĽ½
    -0.08
    èĽIJ
    -0.08
    èĸ¤
    -0.08
    lund
    -0.08
    POSITIVE LOGITS
    èĪ¹ä¸Ĭ
    0.25
     onboard
    0.21
    èĪ¹
    0.20
    车åİ¢
    0.19
    èĪ±
    0.18
    车ä¸Ĭ
    0.18
    ä¹ĺ客
    0.16
     aboard
    0.16
     ship
    0.16
    èĪ·
    0.16
    Activations Density 0.180%

    No Known Activations