© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52161
    Prev
    Next
    INDEX
    Explanations

    into a system or location

    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
    bers
    -0.09
    ward
    -0.09
    ä¸Ģèµ·åİ»
    -0.09
    缮çĿ¹
    -0.08
     ü
    -0.08
    éĿłçĿĢ
    -0.08
    dek
    -0.08
    çŃīåĢĻ
    -0.08
    ãĤĪãģĨãģ«ãģªãģ£ãģŁ
    -0.08
    Ton
    -0.08
    POSITIVE LOGITS
    UBLE
    0.09
    éļį
    0.09
    acı
    0.09
    åľ¨æ¸¸æĪıä¸Ń
    0.09
    ACL
    0.08
    åģļåĪ°äºĨ
    0.08
    ikut
    0.08
    ModelProperty
    0.08
    ìĦŃ
    0.08
    OURCE
    0.08
    Activations Density 0.060%

    No Known Activations