© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53057
    Prev
    Next
    INDEX
    Explanations

    head to, towards, over, out, on, up

    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
    èĪĮå°ĸ
    -0.09
     Tro
    -0.09
    gee
    -0.09
    åĮĻ
    -0.08
    misc
    -0.08
    ä¸Ģåı£
    -0.08
    REE
    -0.08
     baby
    -0.08
    æĢİä¹Īåı¯èĥ½
    -0.08
    å¸®ä½ł
    -0.08
    POSITIVE LOGITS
    çī¢
    0.10
    _singleton
    0.10
    rowse
    0.09
    åĪ°äºĨ
    0.09
    移
    0.09
    achable
    0.09
    olo
    0.09
    é¹Ń
    0.09
    azen
    0.09
    istically
    0.09
    Activations Density 0.005%

    No Known Activations