© 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. 27234
    Prev
    Next
    INDEX
    Explanations

    we want

    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
     ourselves
    -0.11
     myself
    -0.10
    éģį
    -0.10
    çĭ¬å®¶
    -0.09
    ä¸ĢæľŁ
    -0.09
    å¨ĥå¨ĥ
    -0.09
    ä¹Łå¸ĮæľĽ
    -0.09
    /us
    -0.08
    _sv
    -0.08
    宪
    -0.08
    POSITIVE LOGITS
    æĪijçľĭ
    0.11
    æĪijåıĪ
    0.10
    åħ¨å®¶
    0.10
    æĪijåİ»
    0.09
     мне
    0.09
    æĪij
    0.09
    èĭĩ
    0.09
    æĪijæĥ³
    0.09
     Armed
    0.09
    è´¨éĩıéĹ®é¢ĺ
    0.09
    Activations Density 0.221%

    No Known Activations