© 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. 19304
    Prev
    Next
    INDEX
    Explanations

    place names followed by punctuation

    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
     alone
    -0.09
     nor
    -0.09
    åı¦è¡Į
    -0.08
    åĽ½åĬ¡
    -0.08
    tor
    -0.08
    碣
    -0.08
    nor
    -0.08
     Alone
    -0.08
     endregion
    -0.08
     vs
    -0.08
    POSITIVE LOGITS
    å¾Īå¤ļäºĭæĥħ
    0.10
    åı¯ä»¥è¯´æĺ¯
    0.10
    以ä¸ĭç®Ģ称
    0.10
    说å¾Ĺ
    0.10
    iners
    0.10
    INATION
    0.09
    åĥ»
    0.09
    andr
    0.09
    UnderTest
    0.09
    amera
    0.09
    Activations Density 2.939%

    No Known Activations