© 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. 2342
    Prev
    Next
    INDEX
    Explanations

    rainforests and zones

    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
    Õ²
    -0.09
    èļ©
    -0.09
    åħľ
    -0.09
    æºĥ
    -0.09
    éĿ¢æĸĻ
    -0.09
    å¤Ń
    -0.09
    Ñįм
    -0.08
    ç¥ĸ
    -0.08
    åĮĸçŁ³
    -0.08
    çĤİ
    -0.08
    POSITIVE LOGITS
    zone
    0.12
     zone
    0.11
     Zone
    0.11
    zones
    0.10
    åľ¨æĪijåĽ½
    0.10
    Zone
    0.09
    åľ°å¸¦
    0.09
    çĶŁæĢģç³»ç»Ł
    0.09
     zones
    0.09
     trop
    0.09
    Activations Density 0.097%

    No Known Activations