© 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. 33920
    Prev
    Next
    INDEX
    Explanations

    'd' followed by apostrophe

    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
    使ä¹ĭ
    -0.10
     дÑĥÑħ
    -0.10
    ture
    -0.10
    ضة
    -0.09
    SSION
    -0.09
    å¤Ħåľ¨
    -0.09
    anco
    -0.09
    <AM
    -0.09
    aÄŁa
    -0.09
     кÑĢÑĥ
    -0.09
    POSITIVE LOGITS
    à¹Į
    0.13
    å¹´å¤ľ
    0.12
    '
    0.10
    ode
    0.10
    幺
    0.09
    0.09
    ela
    0.08
    ERO
    0.08
    ored
    0.08
    åįłçĶ¨
    0.08
    Activations Density 0.042%

    No Known Activations