© 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. 5834
    Prev
    Next
    INDEX
    Explanations

    nature and earth

    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
     vess
    -0.11
     NIL
    -0.09
    åĩ«
    -0.09
    à¹Ĥย
    -0.09
    æĮĤçĿĢ
    -0.09
    èĻ»
    -0.09
    å¹Ķ
    -0.08
    åīįéĢĶ
    -0.08
     Noon
    -0.08
     маÑĪ
    -0.08
    POSITIVE LOGITS
    大èĩªçĦ¶
    0.25
    èĩªçĦ¶çķĮ
    0.17
     Nature
    0.16
     nature
    0.15
    èĩªçĦ¶
    0.15
    Nature
    0.14
    å¤§åľ°
    0.14
     Natur
    0.13
     natur
    0.13
    nature
    0.11
    Activations Density 0.084%

    No Known Activations