© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51163
    Prev
    Next
    INDEX
    Explanations

    phil

    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
    ilon
    -0.11
    Ñħа
    -0.10
    å¤©åºľ
    -0.09
    eer
    -0.09
    ements
    -0.09
     ÑĦиг
    -0.09
    ingly
    -0.09
    社ä¼ļå®ŀè·µ
    -0.09
    íķij
    -0.09
    çİĩ
    -0.08
    POSITIVE LOGITS
    osopher
    0.15
    adelphia
    0.15
    osoph
    0.13
    aceous
    0.11
    ippines
    0.11
    ament
    0.10
    -economic
    0.10
    ovolta
    0.10
    strate
    0.09
    ocop
    0.09
    Activations Density 0.063%

    No Known Activations