© 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. 35474
    Prev
    Next
    INDEX
    Explanations

    partial words and their continuations

    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
     verge
    -0.10
    è®¤çľŁåŃ¦ä¹ł
    -0.09
     Eid
    -0.09
    iness
    -0.09
    çĹĤ
    -0.09
    soever
    -0.08
    anness
    -0.08
    åģļçļĦäºĭ
    -0.08
    ulatory
    -0.08
    头èĦij
    -0.08
    POSITIVE LOGITS
    ity
    0.14
    /full
    0.13
    mente
    0.12
    è¦ĨçĽĸ
    0.10
    ITY
    0.10
    ité
    0.10
    idades
    0.10
    itas
    0.10
    ities
    0.10
     Partial
    0.10
    Activations Density 0.031%

    No Known Activations