© 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. 3430
    Prev
    Next
    INDEX
    Explanations

    Netherlands and Dutch

    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
    mit
    -0.09
    æ³£
    -0.09
    hots
    -0.08
    ist
    -0.08
    aq
    -0.08
    åĵŃæ³£
    -0.08
    管å§Ķä¼ļ
    -0.08
    hort
    -0.08
    acl
    -0.08
    quier
    -0.08
    POSITIVE LOGITS
    佬
    0.15
    çĦ¶æĺ¯
    0.13
    lify
    0.12
    ness
    0.12
    boro
    0.11
    ovid
    0.10
    ematic
    0.10
    ener
    0.10
    intosh
    0.10
    ocolate
    0.10
    Activations Density 0.012%

    No Known Activations