© 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. 61784
    Prev
    Next
    INDEX
    Explanations

    fortress, search, foot, water, adventures, deal

    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
    typing
    -0.10
    æĽ°
    -0.09
    inceton
    -0.09
    /New
    -0.09
    å¼ķ
    -0.08
    è§Ī
    -0.08
    ëıħ
    -0.08
     AppConfig
    -0.08
    .kotlin
    -0.08
    ozo
    -0.08
    POSITIVE LOGITS
    çŃı
    0.10
    æĮĤéĴ©
    0.10
    igos
    0.09
    è¹²
    0.09
    æ¯ıèĤ¡
    0.09
    æĭį
    0.09
    uctor
    0.09
    èķī
    0.09
    åħ¬åħĥåīį
    0.09
    é¾ĭ
    0.09
    Activations Density 0.083%

    No Known Activations