© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36041
    Prev
    Next
    INDEX
    Explanations

    new or little followed by noun

    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
    çĴŁ
    -0.09
    轻微
    -0.09
    åĴ¬
    -0.09
    æīįæĺ¯çľŁæŃ£
    -0.09
    åİ¢
    -0.08
     dome
    -0.08
    çī¹èī²å°ıéķĩ
    -0.08
    ÂŃing
    -0.08
    æѤç§į
    -0.08
    Expires
    -0.08
    POSITIVE LOGITS
    æī°
    0.09
    lesc
    0.09
    å¹´åIJİ
    0.09
    好åIJĹ
    0.08
    zung
    0.08
    thesize
    0.08
    ths
    0.08
    Browsable
    0.08
    äºĭåIJİ
    0.08
    zzo
    0.08
    Activations Density 0.036%

    No Known Activations