© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19692
    Prev
    Next
    INDEX
    Explanations

    cost effective/saving

    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
    åĬŁå¤«
    -0.12
    ../../../
    -0.12
    ../../
    -0.11
    ending
    -0.11
    onis
    -0.10
    eters
    -0.10
    halt
    -0.10
    ush
    -0.10
    جاÙħ
    -0.09
    laces
    -0.09
    POSITIVE LOGITS
    liest
    0.13
    less
    0.12
    lier
    0.11
    fully
    0.11
    metic
    0.11
    é«ĺæĺĤ
    0.11
    uming
    0.11
    ochond
    0.10
    rength
    0.10
    spiel
    0.10
    Activations Density 0.044%

    No Known Activations