© 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. 32411
    Prev
    Next
    INDEX
    Explanations

    amplified polymorphic markers and RNA fragments

    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
    ACE
    -0.09
    ÙĬÙĪÙĨ
    -0.08
    yaw
    -0.08
     Panc
    -0.08
    _=
    -0.08
    èݹ
    -0.08
    иÑĪÑĮ
    -0.08
    AFE
    -0.08
    ozo
    -0.08
    æ¸ħæĸ°
    -0.08
    POSITIVE LOGITS
    æīĵå¾Ĺ
    0.10
    æłĩå¿ĹæĢ§
    0.10
    失踪
    0.09
    ä¿Ŀå®Ī
    0.09
    ä¸įä¸Ĭ
    0.08
     Marker
    0.08
    åħ¥åѦ
    0.08
    åIJĮ
    0.08
    markers
    0.08
    å±±åİ¿
    0.08
    Activations Density 0.500%

    No Known Activations