© 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. 48051
    Prev
    Next
    INDEX
    Explanations

    to preposition followed by noun/pronoun

    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
    æī¶è´«å·¥ä½ľ
    -0.10
     Quint
    -0.09
     Dou
    -0.08
    Ñģкоп
    -0.08
    çĨ¬
    -0.08
    ëŀĺ
    -0.08
    å°ijè§ģ
    -0.08
    å¯¹æľªæĿ¥
    -0.08
    ÑģÑĤÑĭ
    -0.08
    对åħ¬åı¸
    -0.08
    POSITIVE LOGITS
    ä¸ĸ人
    0.12
    Ãłng
    0.10
    porte
    0.09
    çIJ®
    0.09
    .eye
    0.09
    è·
    0.09
     fullest
    0.09
    edBy
    0.09
    æľĿ
    0.09
    ensed
    0.09
    Activations Density 0.132%

    No Known Activations