© 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. 49787
    Prev
    Next
    INDEX
    Explanations

    coast or shoreline descriptions

    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
    èĪªæµ·
    -0.11
    UCE
    -0.10
    æĪĺåľº
    -0.10
     Rubio
    -0.10
    asco
    -0.10
     nóng
    -0.10
    éģ
    -0.10
    æ¿Ģæĥħ
    -0.10
    æļĤ
    -0.10
    enty
    -0.10
    POSITIVE LOGITS
    æľį
    0.09
     Marg
    0.08
     margin
    0.08
     airs
    0.08
     marginal
    0.08
     labs
    0.08
    æķ²
    0.08
    绦
    0.08
     th
    0.08
     structures
    0.08
    Activations Density 0.060%

    No Known Activations