© 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. 59028
    Prev
    Next
    INDEX
    Explanations

    configuration and setup

    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
    å°»
    -0.10
    imit
    -0.10
    clar
    -0.10
    ä»ŀ
    -0.09
    -quarters
    -0.09
    quis
    -0.09
    fold
    -0.09
    hausen
    -0.09
    iac
    -0.08
    iness
    -0.08
    POSITIVE LOGITS
    urations
    0.20
    urator
    0.17
    ally
    0.15
    ration
    0.13
    uracion
    0.13
    urable
    0.13
    ured
    0.11
    URED
    0.11
    pus
    0.10
    ément
    0.10
    Activations Density 0.061%

    No Known Activations