© 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. 57939
    Prev
    Next
    INDEX
    Explanations

    plastic items

    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
    éľľ
    -0.09
    è°´
    -0.09
    nings
    -0.09
    /pm
    -0.09
    resses
    -0.09
    cation
    -0.09
    èį»
    -0.09
    oused
    -0.09
    luent
    -0.09
    strup
    -0.09
    POSITIVE LOGITS
    ity
    0.13
    ITY
    0.12
    agem
    0.12
    burgh
    0.10
    ìļĶ
    0.09
    ×ķת
    0.08
    idad
    0.08
    uous
    0.08
    ities
    0.08
    ique
    0.08
    Activations Density 0.018%

    No Known Activations