© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51742
    Prev
    Next
    INDEX
    Explanations

    its + completing state

    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
    åħ¶
    -0.11
    åıĬåħ¶
    -0.11
    åħ¶æīĢ
    -0.10
    对çŃĸ
    -0.10
    å®ĥ们
    -0.09
    ç½²
    -0.09
    åĽłåħ¶
    -0.09
    _dash
    -0.09
    èĦijæµ·
    -0.08
    osen
    -0.08
    POSITIVE LOGITS
     entirety
    0.12
    PURE
    0.09
    åĪĸ
    0.09
    è¾ĩ
    0.09
    appropri
    0.08
    æıŃ
    0.08
    è®´
    0.08
     Patty
    0.08
    绶
    0.08
     appropriately
    0.08
    Activations Density 0.061%

    No Known Activations