© 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. 26672
    Prev
    Next
    INDEX
    Explanations

    directions (right, left, on, off)

    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
     lâu
    -0.09
     THROUGH
    -0.09
    ignon
    -0.09
    ä¸įè§ģ
    -0.09
    orney
    -0.09
    iena
    -0.08
    åIJİåı°
    -0.08
    ified
    -0.08
    ied
    -0.08
    åħĥå®Ŀ
    -0.08
    POSITIVE LOGITS
     Recover
    0.08
    ä»»
    0.08
    acr
    0.08
    ÅĪ
    0.08
    为ä¸ŃåĽ½
    0.08
    æĬķåħ¥åĪ°
    0.08
    .getMap
    0.08
    -kind
    0.08
    ä¹°
    0.08
    aval
    0.07
    Activations Density 0.009%

    No Known Activations