© 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. 26807
    Prev
    Next
    INDEX
    Explanations

    proximal, distal, anterior, rostral

    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
    åħīè¾ī
    -0.09
    è·¡
    -0.09
    ÙĦاÙĨ
    -0.09
    æľ¯åIJİ
    -0.09
    0
    -0.09
    åŀŃ
    -0.08
    HA
    -0.08
    åĪĿæģĭ
    -0.08
    3
    -0.08
    åIJı
    -0.08
    POSITIVE LOGITS
    -most
    0.15
    most
    0.14
    ward
    0.11
    WARDS
    0.11
    wards
    0.11
    -facing
    0.11
    éķĽ
    0.11
    éĥ¨åĪĨ
    0.10
    coni
    0.10
    UMB
    0.10
    Activations Density 0.328%

    No Known Activations