© 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. 31438
    Prev
    Next
    INDEX
    Explanations

    adverbs of degree modifying adjectives

    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
    åĭĩäºİ
    -0.11
    åĴ«
    -0.11
    ä¸įå°ıçļĦ
    -0.10
    说å¾Ĺ
    -0.10
    ä¸įå°ı
    -0.10
    çľĭå¾Ĺ
    -0.10
    åħ¬çĦ¶
    -0.10
    åĪ©åĻ¨
    -0.10
    å¿ħè¦ģçļĦ
    -0.09
    PMC
    -0.09
    POSITIVE LOGITS
    ith
    0.10
    arge
    0.09
    èѬå¦Ĥ
    0.08
    CRET
    0.08
    对çŃĸ
    0.08
    arm
    0.08
    å¸ħ
    0.08
    å¤ı
    0.08
    hoe
    0.08
    ousel
    0.08
    Activations Density 0.143%

    No Known Activations