© 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. 4267
    Prev
    Next
    INDEX
    Explanations

    mountain peaks and summits

    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
    æ¶Ķ
    -0.09
    é¹
    -0.09
    åĪĩãĤĮ
    -0.08
    ä¸įæĸŃåıijå±ķ
    -0.08
    cee
    -0.08
    纨
    -0.08
    æĬĬèĩªå·±
    -0.08
    为人
    -0.08
    çĮ¬
    -0.08
    idal
    -0.08
    POSITIVE LOGITS
    çĻ»å±±
    0.18
    山顶
    0.16
    æĶĢçĻ»
    0.15
    å±±ä¸Ĭ
    0.14
     summit
    0.14
    å³°
    0.14
     Summit
    0.13
    é«ĺå³°
    0.13
    Mt
    0.11
    eker
    0.11
    Activations Density 0.059%

    No Known Activations