© 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. 27452
    Prev
    Next
    INDEX
    Explanations

    disaster and emergency response

    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
    éŀį
    -0.09
    miner
    -0.09
    ä¹ŁæŃ£æĺ¯
    -0.09
    zyst
    -0.09
    èĪ¾
    -0.08
    ismet
    -0.08
    -guard
    -0.08
    peat
    -0.08
    å¥ĩå¦Ļ
    -0.08
    è¶ħé¢Ŀ
    -0.08
    POSITIVE LOGITS
    åĪ°æŶåĢĻ
    0.11
    çĺ«
    0.10
    ashes
    0.09
    é¡·
    0.09
    å±ĬæŶ
    0.09
    usi
    0.09
    ä»»ä½ķæŶåĢĻ
    0.09
    å¤Ħç½®
    0.09
    åħ¨ä½ĵ
    0.09
    ignum
    0.09
    Activations Density 0.079%

    No Known Activations