© 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. 8418
    Prev
    Next
    INDEX
    Explanations

    ruin and its variations, destroy

    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
    è¨Ĺ
    -0.09
    ä¾ij
    -0.08
    éĹ¼
    -0.08
    çĮ¥
    -0.08
    igi
    -0.08
    ä¸įæ¸ħ
    -0.08
     Accom
    -0.08
    óng
    -0.08
    åĪ°æľŁ
    -0.08
    inst
    -0.08
    POSITIVE LOGITS
    fried
    0.09
    åĽŀå¿Ĩ
    0.09
     havoc
    0.09
    åİŁæľīçļĦ
    0.09
    ope
    0.09
    å¼Ģ端
    0.09
    illo
    0.08
    ìķĮ
    0.08
    ruk
    0.08
    ously
    0.08
    Activations Density 0.015%

    No Known Activations