© 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. 17929
    Prev
    Next
    INDEX
    Explanations

    eager or keen to

    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
    iw
    -0.09
    lev
    -0.09
    è¾Ľè¾£
    -0.08
    /Open
    -0.08
    主è¦ģåĨħ容
    -0.08
    æĬĺå°Ħ
    -0.08
    level
    -0.08
    .aut
    -0.08
    -Level
    -0.08
    ort
    -0.08
    POSITIVE LOGITS
     ÑģоÑħ
    0.11
    åľ°è¯´
    0.11
     à¹Ĩ
    0.10
    æĬķ身
    0.10
    å·²ä¹ħçļĦ
    0.10
    à¸Ńà¸Ļ
    0.10
     enough
    0.10
    åľ°å¸¦
    0.10
    å·²ä¹ħ
    0.10
    糧
    0.10
    Activations Density 0.010%

    No Known Activations