© 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. 53398
    Prev
    Next
    INDEX
    Explanations

    i.e. or example

    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
    çħ§
    -0.09
    åŦ
    -0.08
    çīĮåŃIJ
    -0.08
    å¿ĥåĬ¨
    -0.08
    rok
    -0.08
     Paz
    -0.08
    çħ§é¡¾
    -0.08
    anal
    -0.08
    illon
    -0.08
     Cong
    -0.08
    POSITIVE LOGITS
    è¾Ĺ转
    0.10
    æľīåºıæİ¨è¿Ľ
    0.10
    å¼Ĥåľ°
    0.10
    èĿ¼
    0.09
    äge
    0.09
    åĪį
    0.09
    éķ¿éĢĶ
    0.09
    üb
    0.08
     Britt
    0.08
    ä¹ĭéĻħ
    0.08
    Activations Density 0.149%

    No Known Activations