© 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. 39099
    Prev
    Next
    INDEX
    Explanations

    numbers close to zero or one

    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
    Į¨
    -0.11
    纰
    -0.09
    orris
    -0.09
    odom
    -0.09
    åij·
    -0.08
    å½»
    -0.08
    æŃ»
    -0.08
    çłĴ
    -0.08
    åĬŀäºĭå¤Ħ
    -0.08
    纳
    -0.08
    POSITIVE LOGITS
    çĶ¸
    0.10
    éĺħ
    0.10
    à°³
    0.10
     League
    0.09
    æ¡£
    0.09
    ноÑģÑĤ
    0.09
    ÙĪÙĬ
    0.08
    erno
    0.08
     Larson
    0.08
     Honest
    0.08
    Activations Density 0.060%

    No Known Activations