© 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. 18752
    Prev
    Next
    INDEX
    Explanations

    shift current, shift from

    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
    ãĥijãĤ¹
    -0.09
    åħijæį¢
    -0.09
    éĴµ
    -0.09
    atas
    -0.09
    çĽĴ
    -0.09
    æī¹ç¤º
    -0.08
    _GF
    -0.08
    uib
    -0.08
    åIJĮè¡Į
    -0.08
    akit
    -0.08
    POSITIVE LOGITS
    (shift
    0.14
     focus
    0.13
     shift
    0.12
     shifts
    0.12
    éĩįå¿ĥ
    0.11
     SHIFT
    0.11
     gears
    0.11
    -shift
    0.11
     shifted
    0.10
    shift
    0.10
    Activations Density 0.028%

    No Known Activations