© 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. 35209
    Prev
    Next
    INDEX
    Explanations

    murder, pit, crunch, night, memory, day, water, angel, rainbow

    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¶Ĭæĺ¯
    -0.10
    æºī
    -0.10
    çĭĴ
    -0.09
    ihan
    -0.09
    åİĭ
    -0.09
    ħĮ
    -0.09
    太éĺ³èĥ½
    -0.09
    èħ°éĥ¨
    -0.09
    /static
    -0.09
    ä¼ī
    -0.09
    POSITIVE LOGITS
     hall
    0.10
     fame
    0.09
    åİħ
    0.08
     Dangerous
    0.08
    uild
    0.08
    aign
    0.08
     Peak
    0.08
     Eug
    0.08
    æŀĦæĢĿ
    0.08
     junction
    0.08
    Activations Density 0.213%

    No Known Activations