© 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. 2961
    Prev
    Next
    INDEX
    Explanations

    Indian states and foreign characters

    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
    деÑģÑıÑĤ
    -0.10
    媳
    -0.10
    ìį¨
    -0.10
    omorphic
    -0.10
    mith
    -0.10
    ãģĮãĤī
    -0.09
     thợ
    -0.09
    orted
    -0.09
     hẳn
    -0.09
    ently
    -0.09
    POSITIVE LOGITS
    ily
    0.12
    ured
    0.11
    ened
    0.10
    uring
    0.10
    ening
    0.09
    Tween
    0.09
    ists
    0.09
    è§İ
    0.09
    åķī
    0.09
    ulary
    0.08
    Activations Density 0.296%

    No Known Activations