© 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. 11752
    Prev
    Next
    INDEX
    Explanations

    steering, guidance, control

    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
    lij
    -0.09
    伤çĹħ
    -0.09
    æĭħ
    -0.09
    icals
    -0.09
    æĭħå½ĵ
    -0.08
     Quincy
    -0.08
    å·½
    -0.08
    æĵĶ
    -0.08
     Masc
    -0.08
    rug
    -0.08
    POSITIVE LOGITS
    æĮĩå¼ķ
    0.13
    åѦç§ij
    0.12
     steering
    0.12
    导èĪª
    0.11
    æݧåĪ¶
    0.11
     guidance
    0.11
    驾é©Ń
    0.11
    èĩªå¦Ĥ
    0.11
     control
    0.10
     guid
    0.10
    Activations Density 0.089%

    No Known Activations