© 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. 29967
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns

    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
    大家åĪĨ享
    -0.11
    æľ¬æĬ¥
    -0.11
    æľĭåıĭ们对
    -0.10
    çī¹æ®ĬæĥħåĨµ
    -0.09
    èĪ¶
    -0.09
    rovers
    -0.09
    çĺ¾
    -0.09
    空æ°Ķä¸Ń
    -0.08
    áī¤
    -0.08
    ropriate
    -0.08
    POSITIVE LOGITS
    ons
    0.08
     prm
    0.08
    eva
    0.08
    æĶ¾å¿ĥ
    0.08
    wn
    0.08
    essen
    0.07
    loud
    0.07
    ev
    0.07
    SELF
    0.07
    implicitly
    0.07
    Activations Density 0.357%

    No Known Activations