© 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. 26708
    Prev
    Next
    INDEX
    Explanations

    specific language governing

    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
    lop
    -0.10
    istani
    -0.09
    ingly
    -0.09
    OrUpdate
    -0.09
    ï¸
    -0.09
    pla
    -0.09
    loads
    -0.09
    rit
    -0.09
    å¾Ĺä½ı
    -0.09
    IMUM
    -0.09
    POSITIVE LOGITS
    auge
    0.15
    0.13
    çĻĸ
    0.10
     franca
    0.09
    oda
    0.09
    arrison
    0.09
    UNCH
    0.09
    ous
    0.09
    =en
    0.09
    caster
    0.09
    Activations Density 0.112%

    No Known Activations