© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51150
    Prev
    Next
    INDEX
    Explanations

    conjunctions and meanwhile

    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
    mate
    -0.09
    çĭ±
    -0.09
    头èĦij
    -0.09
    åľ¨å½ĵåľ°
    -0.08
    enger
    -0.08
    æŃ¤äºº
    -0.08
    è¿ĻåIJį
    -0.08
    éĢļæĬ¥
    -0.08
    åıijå±ķæĪĺçķ¥
    -0.08
    夥
    -0.08
    POSITIVE LOGITS
    èĢĮ
    0.15
    ãģªãģĮãĤī
    0.12
     others
    0.12
    others
    0.12
    èĢĮåĩº
    0.11
    ãģ§ãģĻãģĹ
    0.10
    Meanwhile
    0.10
    èĢĮå·²
    0.10
     meanwhile
    0.10
     iar
    0.10
    Activations Density 0.220%

    No Known Activations