© 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. 36699
    Prev
    Next
    INDEX
    Explanations

    successor and predecessor roles

    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
    yna
    -0.11
    身价
    -0.10
    agh
    -0.10
    agna
    -0.10
    èļĵ
    -0.10
    æıIJåīį
    -0.09
    mess
    -0.09
    onne
    -0.09
    è¿ĩåIJİ
    -0.09
    åīįç½®
    -0.09
    POSITIVE LOGITS
    hip
    0.11
    ively
    0.11
    ably
    0.10
    hin
    0.09
    ship
    0.09
    äºĨä¸įå°ij
    0.08
    輩
    0.08
    çĻ»
    0.08
    ниÑĨа
    0.08
    chaft
    0.08
    Activations Density 0.015%

    No Known Activations