© 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. 56944
    Prev
    Next
    INDEX
    Explanations

    software, reader, systems

    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
    æı©
    -0.08
    andre
    -0.08
     bumper
    -0.08
    é¹ŀ
    -0.08
     khá»ı
    -0.08
    scribe
    -0.08
    isc
    -0.08
     pole
    -0.08
    æĤ¬æĮĤ
    -0.08
    Ñįм
    -0.08
    POSITIVE LOGITS
    esz
    0.12
    ENTS
    0.10
    oz
    0.09
    UNCH
    0.09
    AIL
    0.09
    æ¡Ħ
    0.09
    fighters
    0.09
    rocket
    0.09
    urd
    0.09
    _Runtime
    0.08
    Activations Density 0.003%

    No Known Activations