© 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. 7894
    Prev
    Next
    INDEX
    Explanations

    capacitive touch

    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
     videot
    -0.09
    æijĦ
    -0.09
    .ship
    -0.09
    iker
    -0.08
     Spare
    -0.08
    hil
    -0.08
    å°±è¿Ļæł·
    -0.08
    楣
    -0.08
    ,[],
    -0.08
    asje
    -0.08
    POSITIVE LOGITS
     touch
    0.12
    -touch
    0.11
    .touch
    0.11
    æīª
    0.10
    ationToken
    0.09
    触æij¸
    0.09
    touch
    0.09
    åĨ°éĽª
    0.09
     Finger
    0.09
    æĦŁåºĶ
    0.09
    Activations Density 0.105%

    No Known Activations