© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21527
    Prev
    Next
    INDEX
    Explanations

    tapping or tapped out

    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
    liness
    -0.09
    ä¸Ģå®ļç¨ĭ度
    -0.08
    åĭĸ
    -0.08
    æĮŁ
    -0.08
     Sheridan
    -0.08
    å®īæħ°
    -0.08
    交åıī
    -0.08
    visibility
    -0.08
    诸èijĽ
    -0.08
    说æĪij
    -0.08
    POSITIVE LOGITS
     taps
    0.10
    OrCreate
    0.10
     tapping
    0.09
    à¹ĥà¸Ī
    0.09
    orial
    0.09
    tap
    0.09
    STONE
    0.09
    æĥħæĻ¯
    0.08
    geber
    0.08
    recision
    0.08
    Activations Density 0.010%

    No Known Activations