© 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. 55402
    Prev
    Next
    INDEX
    Explanations

    bit urls and bitbucket

    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
    ä¸įäºĨ
    -0.09
     tus
    -0.09
    azi
    -0.09
    noon
    -0.09
    hin
    -0.08
    etic
    -0.08
    eer
    -0.08
    çŀ¿
    -0.08
    hip
    -0.08
    stration
    -0.08
    POSITIVE LOGITS
    ting
    0.13
    /stdc
    0.13
    tern
    0.13
    umen
    0.13
    åı¯æĥľ
    0.12
    PerPixel
    0.12
    iful
    0.12
    åĦ¿
    0.12
    ÑĩиÑģлен
    0.12
    rix
    0.11
    Activations Density 0.054%

    No Known Activations