© 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. 54777
    Prev
    Next
    INDEX
    Explanations

    brief description

    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
    /OR
    -0.10
    thic
    -0.10
    aje
    -0.10
    /her
    -0.09
    è¸Ĭè·ĥ
    -0.09
     eventual
    -0.09
    ocratic
    -0.09
    hed
    -0.09
    al
    -0.08
    IZED
    -0.08
    POSITIVE LOGITS
    ly
    0.11
    ness
    0.11
    -lived
    0.10
    /small
    0.10
    istan
    0.10
    lest
    0.10
    Enough
    0.10
    ä¸ĢçĤ¹
    0.09
    èĢĮåıĪ
    0.09
    otto
    0.09
    Activations Density 0.022%

    No Known Activations