© 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. 21053
    Prev
    Next
    INDEX
    Explanations

    php, .php, php-ids, php-ids.org, php.func

    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
    åŃIJéĩĮ
    -0.09
    ľ
    -0.09
    ascade
    -0.08
    nia
    -0.08
    飧
    -0.08
    меÑĤ
    -0.08
     hundred
    -0.08
    èľĩ
    -0.08
    оÑģ
    -0.08
    èŀ«
    -0.08
    POSITIVE LOGITS
    ../../../
    0.16
    ãģĦãģĨ
    0.11
    yard
    0.11
    asure
    0.10
    oses
    0.10
    ion
    0.10
    aceous
    0.09
    æľĪåĪĿ
    0.09
    ī
    0.08
    èĭĵ
    0.08
    Activations Density 0.312%

    No Known Activations