© 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. 30167
    Prev
    Next
    INDEX
    Explanations

    out there; position; location

    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
    çĤķ
    -0.10
    åħ¥çĿ¡
    -0.09
    è£Ĩ
    -0.09
    æŁ¬
    -0.09
    æľ«
    -0.09
    abox
    -0.08
     Carpet
    -0.08
    éĤĥ
    -0.08
    omid
    -0.08
    æŃ»è§Ĵ
    -0.08
    POSITIVE LOGITS
    è¦ģæľī
    0.09
    NST
    0.09
    åıijè¨Ģ
    0.09
    gest
    0.09
    çĽĸ
    0.08
    æĦŁãģĺãĤĭ
    0.08
    ẩu
    0.08
     BRAND
    0.08
    alem
    0.08
    æĻļ
    0.08
    Activations Density 0.004%

    No Known Activations