© 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. 27986
    Prev
    Next
    INDEX
    Explanations

    cars and automotive products

    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
    æī¿
    -0.11
    æŃ©
    -0.09
    irit
    -0.09
    æĭĦ
    -0.09
    ews
    -0.08
    çŁŃ线
    -0.08
    çħ¤æ°Ķ
    -0.08
    irim
    -0.08
     pet
    -0.08
    æķ£æŃ¥
    -0.08
    POSITIVE LOGITS
    èĩ§
    0.11
    Cars
    0.10
    汽车
    0.10
     car
    0.10
    ä¸ŃåĽ½æ±½è½¦
    0.10
     Automotive
    0.10
    è¾Ĩ车
    0.10
    æ±½è»Ĭ
    0.10
    çIJ
    0.10
    车è¾Ĩ
    0.09
    Activations Density 0.141%

    No Known Activations