© 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. 5854
    Prev
    Next
    INDEX
    Explanations

    block or street address

    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
    家åĽŃ
    -0.10
    odic
    -0.09
    otime
    -0.09
    è¿Ļ家
    -0.09
    èĨ³
    -0.09
    ầy
    -0.09
    éĻĦ
    -0.09
    odo
    -0.09
    èĩªåıij
    -0.09
    éħ½
    -0.09
    POSITIVE LOGITS
    躬
    0.09
    ading
    0.09
    inding
    0.09
    èµ°åħ¥
    0.08
    -long
    0.08
    åĨħçļĦ
    0.08
    _pg
    0.08
    åĪ·
    0.08
    glomer
    0.08
    atat
    0.07
    Activations Density 0.002%

    No Known Activations