© 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. 4354
    Prev
    Next
    INDEX
    Explanations

    personal information

    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
    ÑĢаÑĤ
    -0.10
    yard
    -0.10
    uer
    -0.10
    roots
    -0.09
    yards
    -0.09
     havoc
    -0.09
    erness
    -0.09
    è®¤çľŁåŃ¦ä¹ł
    -0.08
    人éĢł
    -0.08
    /she
    -0.08
    POSITIVE LOGITS
    nel
    0.12
    nels
    0.12
    ities
    0.11
    nal
    0.11
    ality
    0.10
    /person
    0.10
    (person
    0.10
    hood
    0.10
    åĮĸçļĦ
    0.10
    (Person
    0.10
    Activations Density 0.055%

    No Known Activations