© 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. 63544
    Prev
    Next
    INDEX
    Explanations

    experimental study findings

    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
    -0.12
    åĤ»
    -0.09
    onia
    -0.08
    åµĺ
    -0.08
    ÑıÑģÑĮ
    -0.08
    åħĪçĶŁ
    -0.08
    avan
    -0.08
    赤
    -0.08
    ино
    -0.08
    æľ¯
    -0.08
    POSITIVE LOGITS
    å¼Ģåĩº
    0.10
    ãģªãģĦãģ¨
    0.09
    导读
    0.09
    _IOS
    0.09
    annis
    0.09
    å®īåįĵ
    0.09
    éĤĥ
    0.09
    ntl
    0.09
    ined
    0.08
    ists
    0.08
    Activations Density 0.056%

    No Known Activations