© 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. 48784
    Prev
    Next
    INDEX
    Explanations

    steam or steampunk

    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
    åħ¬å¼Ģ课
    -0.10
    anker
    -0.10
    éĶĭ
    -0.09
    ocations
    -0.09
    åĨ»
    -0.09
    æ¿Ģ
    -0.09
    _CHAIN
    -0.09
    泫
    -0.09
    å¸ĪèĮĥ大åѦ
    -0.09
     Seal
    -0.08
    POSITIVE LOGITS
     gob
    0.11
    è§Ĵèī²
    0.08
    edImage
    0.08
    rial
    0.08
    dio
    0.08
    ष
    0.08
    ä¸Ńéĵģ
    0.08
    éĿ¢åħ·
    0.08
    èĬĴ
    0.08
    glass
    0.08
    Activations Density 0.002%

    No Known Activations