© 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. 61194
    Prev
    Next
    INDEX
    Explanations

    rental

    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
    est
    -0.15
    ively
    -0.14
    lessly
    -0.12
    ally
    -0.12
    ening
    -0.11
    aling
    -0.10
    ðŁı»
    -0.10
    es
    -0.09
    esc
    -0.09
    onaut
    -0.09
    POSITIVE LOGITS
    itch
    0.12
    icious
    0.10
    /rem
    0.10
    æѤåĪ»
    0.10
    ambda
    0.10
    sek
    0.10
    ÑĤоÑĢ
    0.09
    the
    0.09
    ogue
    0.09
    thing
    0.09
    Activations Density 0.004%

    No Known Activations