© 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. 62989
    Prev
    Next
    INDEX
    Explanations

    outstanding noun usage

    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
    osoph
    -0.10
    boat
    -0.10
    bies
    -0.09
    è¯ļæĦı
    -0.09
    éĴĩ
    -0.09
    ä»ĵ
    -0.08
    anth
    -0.08
    ack
    -0.08
    å¤ĦåĪĨ
    -0.08
    ods
    -0.08
    POSITIVE LOGITS
    ly
    0.15
    çĪ°
    0.12
    edBy
    0.10
    åīįèĢħ
    0.10
    åIJİèĢħ
    0.10
    ed
    0.10
    lish
    0.09
    ness
    0.09
    妣
    0.09
    æ±Łæ·®
    0.09
    Activations Density 0.005%

    No Known Activations