© 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. 55611
    Prev
    Next
    INDEX
    Explanations

    height, km, rebels, low, US, opposition

    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
     Pitch
    -0.08
    upal
    -0.08
     pitch
    -0.08
    ius
    -0.08
    pitch
    -0.08
    åĤ¬
    -0.08
     Autos
    -0.08
     Hy
    -0.08
    EPS
    -0.08
    åºĬä¸Ĭ
    -0.08
    POSITIVE LOGITS
    èĥ¥
    0.11
    ettes
    0.10
    oyer
    0.10
    ikes
    0.09
    çģµéŃĤ
    0.09
     altitude
    0.09
    erez
    0.09
    確ãģĭãģ«
    0.09
    ahr
    0.09
    å®ĺæĸ¹
    0.09
    Activations Density 0.096%

    No Known Activations