© 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. 57139
    Prev
    Next
    INDEX
    Explanations

    directly followed by prepositions

    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
    çĦ¶æĺ¯
    -0.10
    楫
    -0.10
    weise
    -0.09
    ruc
    -0.09
    çĶļ
    -0.09
    æ¦Ķ
    -0.08
    prit
    -0.08
    èī°å·¨
    -0.08
    åį³å°ĨåĪ°æĿ¥
    -0.08
    erie
    -0.08
    POSITIVE LOGITS
    åĪ¹
    0.10
    olley
    0.09
    -handed
    0.08
    蹦
    0.08
    eced
    0.08
    _FOLLOW
    0.08
    宿èĪį
    0.08
     Sadd
    0.08
    å¯Ŀ室
    0.08
    ãģ¾ãģĹãģ¦
    0.08
    Activations Density 0.017%

    No Known Activations