© 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. 9157
    Prev
    Next
    INDEX
    Explanations

    add its view

    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
    çĶ¨å·¥
    -0.08
    åĴ«
    -0.08
    VED
    -0.08
    ç¦Ħ
    -0.08
     Robbins
    -0.08
    ä¸į便
    -0.08
    æľī害
    -0.08
    æģIJæħĮ
    -0.08
    csi
    -0.08
    itus
    -0.07
    POSITIVE LOGITS
    çĻ£
    0.09
    çīĴ
    0.09
    reat
    0.09
    _race
    0.09
     didFinish
    0.09
    âĴ¸
    0.09
    _pf
    0.09
    åľ¨è¿ĩ渡
    0.08
    _Pr
    0.08
    irut
    0.08
    Activations Density 1.652%

    No Known Activations