© 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. 19226
    Prev
    Next
    INDEX
    Explanations

    when someone, people, your

    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
    å¾Īæľīåı¯èĥ½
    -0.10
    å¾Īåı¯èĥ½
    -0.10
    使ä¹ĭ
    -0.09
    likely
    -0.09
    äºĨä¸įå°ij
    -0.09
    HAL
    -0.08
    åģļè¿ĩ
    -0.08
    è°¤
    -0.08
    éĥ¨åĪĨåľ°åĮº
    -0.08
    å¾Īéĩįè¦ģçļĦ
    -0.08
    POSITIVE LOGITS
    nw
    0.09
    Fil
    0.09
     заÑıв
    0.09
    æĻ¯çĤ¹
    0.09
    olds
    0.09
    æĻ¯åĮº
    0.09
    çĮľ
    0.08
    çIJĨè´¢
    0.08
    edly
    0.08
    egg
    0.08
    Activations Density 0.057%

    No Known Activations