© 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. 4988
    Prev
    Next
    INDEX
    Explanations

    names ending in ian

    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
    воÑĢ
    -0.11
    ãģ£ãģįãĤĬ
    -0.11
    let
    -0.11
    manship
    -0.09
    lette
    -0.09
    ting
    -0.09
    backs
    -0.09
    /or
    -0.09
    ning
    -0.09
    dit
    -0.09
    POSITIVE LOGITS
    mente
    0.12
    amente
    0.11
    ität
    0.11
    hay
    0.10
    tion
    0.10
    itä
    0.09
    ly
    0.09
    idade
    0.09
    ../../
    0.09
    ãĥ£
    0.08
    Activations Density 0.017%

    No Known Activations