© 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. 52768
    Prev
    Next
    INDEX
    Explanations

    sign or authority

    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
    饯
    -0.10
    opus
    -0.10
    åģ·
    -0.09
    åįĩ
    -0.09
    ä»»æĢ§
    -0.09
    cura
    -0.08
    çĶŁäº§åĬĽ
    -0.08
    _office
    -0.08
    bero
    -0.08
    arris
    -0.08
    POSITIVE LOGITS
    çĻ½å¤©
    0.10
    æ¸ħæĻ°
    0.10
    .struct
    0.10
    èѦåijĬ
    0.09
    èħ±
    0.09
    æĬ¤èº«
    0.09
    åīįä¸Ģ天
    0.09
    å®Įå¤ĩ
    0.08
    åĽ¾ä¸º
    0.08
    èĺijèıĩ
    0.08
    Activations Density 0.060%

    No Known Activations