© 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. 6473
    Prev
    Next
    INDEX
    Explanations

    lateral position

    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
    ardi
    -0.10
    æŁĦ
    -0.10
     gy
    -0.09
    æĥ¨
    -0.09
     Stephens
    -0.09
    rint
    -0.08
    侪
    -0.08
    geb
    -0.08
     gap
    -0.08
    éķĴ
    -0.08
    POSITIVE LOGITS
    åIJijãģį
    0.09
    躺
    0.09
    ãĤĤãģ¡
    0.09
    çĿ¡è§ī
    0.09
    ayah
    0.09
    趴
    0.09
    å¤ļæł·æĢ§
    0.09
    åİ»çľĭçľĭ
    0.09
    èIJĿåįľ
    0.09
    èĦijè¢ĭ
    0.09
    Activations Density 0.045%

    No Known Activations