© 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. 5773
    Prev
    Next
    INDEX
    Explanations

    24-hour

    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
    鹬
    -0.10
    åIJĦèĩªçļĦ
    -0.10
    ä¼ŀ
    -0.10
    onium
    -0.10
    .EntityManager
    -0.10
    觥
    -0.10
    åŁĻ
    -0.09
    å¾ķ
    -0.09
    LEM
    -0.09
    å¤ļå¹´
    -0.09
    POSITIVE LOGITS
    è¾¾æłĩ
    0.10
    .appspot
    0.09
    imensional
    0.08
    atory
    0.08
    MOD
    0.08
    st
    0.08
    åĨĴ
    0.08
    igan
    0.07
    åĭĩ
    0.07
    Ñijм
    0.07
    Activations Density 0.025%

    No Known Activations