© 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. 23691
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by 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
    èĢģå¸ĪçļĦ
    -0.10
    对æĪijæĿ¥è¯´
    -0.09
    èªĵ
    -0.09
    大å§IJ
    -0.09
    åİŁèijĹ
    -0.09
    åĨ³å¿ĥ
    -0.08
    æĢķ
    -0.08
    èĻ½è¯´
    -0.08
     pledge
    -0.08
    enet
    -0.08
    POSITIVE LOGITS
    ç»ıæŁ¥
    0.10
    å¤Ł
    0.10
    åIJ¦
    0.09
    canf
    0.09
    utom
    0.09
    èĩªæ²»
    0.08
    æľ½
    0.08
    ypi
    0.08
    ech
    0.08
     Cv
    0.08
    Activations Density 0.111%

    No Known Activations