© 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. 5657
    Prev
    Next
    INDEX
    Explanations

    Taylor followed by names or places

    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
    ime
    -0.10
    awai
    -0.10
    åĭĥåĭĥ
    -0.09
    ãĥ§ãĥ³
    -0.09
    æľįåĬ¡è´¨éĩı
    -0.09
    иÑĢа
    -0.09
    uous
    -0.09
    yen
    -0.09
    ãģŁãĤģãģ«
    -0.09
    alus
    -0.09
    POSITIVE LOGITS
    ities
    0.15
    -made
    0.12
    à¹Į
    0.11
    izations
    0.11
    atan
    0.11
    ney
    0.11
    ãģ¾ãģĻãģĮ
    0.10
    anager
    0.10
    cess
    0.10
    ization
    0.10
    Activations Density 0.079%

    No Known Activations