© 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. 5381
    Prev
    Next
    INDEX
    Explanations

    patient data and care

    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
    èĿ
    -0.10
    æļ´åĬĽ
    -0.09
    çĿ£å¯¼
    -0.09
    tape
    -0.08
     THEORY
    -0.08
    åıĤä¸İèĢħ
    -0.08
    çĨŁç»ĥ
    -0.08
    dux
    -0.08
    ainer
    -0.08
    åĭĻ
    -0.08
    POSITIVE LOGITS
    å¤įæ´»
    0.09
    ResourceManager
    0.08
    _dirty
    0.08
     antic
    0.08
    ÑĤел
    0.08
    broker
    0.08
    çĻ¾ç§ij
    0.08
    èµĦ产éĩįç»Ħ
    0.08
     Nunes
    0.08
    composite
    0.08
    Activations Density 0.116%

    No Known Activations