© 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. 17956
    Prev
    Next
    INDEX
    Explanations

    it is

    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
    APPED
    -0.11
    å¾Īå¤ļäºĭæĥħ
    -0.11
    åŀ«
    -0.10
    æ¯ĶåĪ©
    -0.10
    以èĩ´
    -0.09
    èļ±
    -0.09
    讫
    -0.09
    æľīæŶåĢĻ
    -0.09
    ages
    -0.09
    hand
    -0.09
    POSITIVE LOGITS
    /do
    0.09
     heter
    0.09
    ниÑĨ
    0.09
    vet
    0.08
    .GetItem
    0.08
    IRO
    0.08
    åħįè²»
    0.08
    uka
    0.08
    aler
    0.08
     Pods
    0.08
    Activations Density 0.093%

    No Known Activations