© 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. 48714
    Prev
    Next
    INDEX
    Explanations

    stitch and suture

    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
    ish
    -0.10
    isle
    -0.09
    plete
    -0.09
    ances
    -0.08
    anche
    -0.08
    Å¡t
    -0.08
    quent
    -0.08
    ance
    -0.08
    forth
    -0.08
    stairs
    -0.08
    POSITIVE LOGITS
    edImage
    0.12
    æ°ijå¿ĥ
    0.12
    punk
    0.11
    edly
    0.10
    pery
    0.09
    RELATED
    0.09
    们çļĦ
    0.09
    гаÑĢ
    0.09
    edList
    0.09
    ãģĵãģ¨ãģ§ãģĻ
    0.09
    Activations Density 0.004%

    No Known Activations