© 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. 53486
    Prev
    Next
    INDEX
    Explanations

    inhabited, subject, Automatic, Net

    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
    äºĮåŃĹ
    -0.10
     Bowman
    -0.09
    ORT
    -0.09
    (es
    -0.09
    ä»ij
    -0.08
    amel
    -0.08
    pio
    -0.08
    à¹ģà¸Ĭ
    -0.08
    è¡£æľį
    -0.08
     à¹Ĩ
    -0.08
    POSITIVE LOGITS
    msp
    0.09
    uchs
    0.08
    ÑĤÑĮ
    0.08
     Flint
    0.08
    shr
    0.08
    âĢ
    0.08
    综åIJĪ
    0.08
     moment
    0.08
    ounder
    0.08
    å¿Ĵ
    0.07
    Activations Density 0.122%

    No Known Activations