© 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. 48295
    Prev
    Next
    INDEX
    Explanations

    possessive noun followed by a noun

    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
    æĿIJ
    -0.11
    ä¸ĢéĿ¢
    -0.10
    éľĩ
    -0.10
    ä¸Ģè´¯
    -0.10
    éľĩåĬ¨
    -0.10
    ãģ¦ãĤĤ
    -0.10
    áĥĹ
    -0.09
    çĥ«
    -0.09
    ish
    -0.09
    æ·±åĮĸæĶ¹éĿ©
    -0.09
    POSITIVE LOGITS
    alan
    0.09
    -ft
    0.09
    SES
    0.09
    .poly
    0.08
    _PP
    0.08
    .weixin
    0.08
    dro
    0.08
    _STRUCT
    0.08
    âĤ¬âĦ¢
    0.08
    iration
    0.08
    Activations Density 0.116%

    No Known Activations