© 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. 48795
    Prev
    Next
    INDEX
    Explanations

    up to date

    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
    ä¸Ģå¦ĤæĹ¢å¾Ģ
    -0.09
    åĪ©äºİ
    -0.09
    ÑģÑĤанов
    -0.08
     downgrade
    -0.08
    edBy
    -0.08
    erin
    -0.08
    aya
    -0.08
    /or
    -0.08
    å¯Į
    -0.08
    åĩºæĿ¥çļĦ
    -0.08
    POSITIVE LOGITS
    为æŃ¢
    0.11
    OrCreate
    0.10
    ÙĦÙĤ
    0.09
    velopment
    0.09
    ANNER
    0.09
    ancock
    0.08
    iname
    0.08
    Ùĭ
    0.08
    åľ¬
    0.08
    -ish
    0.08
    Activations Density 0.007%

    No Known Activations