© 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. 2655
    Prev
    Next
    INDEX
    Explanations

    possessive nouns followed by specific 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
    æĭ¿åĩºæĿ¥
    -0.10
    èľķåıĺ
    -0.10
    亮çĤ¹
    -0.10
    è½½ä½ĵ
    -0.09
    ola
    -0.09
    èĥĮæĻ¯
    -0.08
    ä¼ģä¸ļæıIJä¾Ľ
    -0.08
    ä¸įæŃ¢
    -0.08
    çĹħæĥħ
    -0.08
    仲
    -0.08
    POSITIVE LOGITS
     ability
    0.14
    Ability
    0.12
     attempts
    0.12
     attempt
    0.12
    对ä¸ŃåĽ½
    0.11
    对
    0.11
    对åħ¬åı¸
    0.11
     efforts
    0.11
     иÑģполÑĮзование
    0.10
     inability
    0.10
    Activations Density 0.183%

    No Known Activations