© 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. 61903
    Prev
    Next
    INDEX
    Explanations

    snap or snapping

    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
    éĩįéĩį
    -0.09
    åĨįéĢł
    -0.09
    ØŃر
    -0.09
    â¿
    -0.09
    å®ļçĤ¹
    -0.09
    mmas
    -0.09
    注åĨĮèµĦæľ¬
    -0.08
    çĶļ
    -0.08
    éĢ¡
    -0.08
     mover
    -0.08
    POSITIVE LOGITS
    itude
    0.10
    PEAR
    0.09
    çīĴ
    0.09
    åľ¨çĶŁæ´»ä¸Ń
    0.09
    ä¾ĥ
    0.08
    oints
    0.08
    渡
    0.08
    Snap
    0.08
    pear
    0.08
    resent
    0.08
    Activations Density 0.020%

    No Known Activations