© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50723
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions with following words

    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
    /or
    -0.10
    è¾Ħ
    -0.10
    2
    -0.09
    æľĭåıĭ们
    -0.09
    1
    -0.09
    4
    -0.08
    8
    -0.08
    6
    -0.08
    è®®
    -0.08
    9
    -0.08
    POSITIVE LOGITS
    orem
    0.14
    è·Łå¥¹
    0.11
    atables
    0.11
     Cbd
    0.10
    oretical
    0.10
    icial
    0.09
    naments
    0.09
    æĬĢæľ¯æ°´å¹³
    0.09
    个人è§ĤçĤ¹
    0.09
    èĥ³
    0.09
    Activations Density 0.260%

    No Known Activations