© 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. 2272
    Prev
    Next
    INDEX
    Explanations

    newly + past participle

    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
    spiel
    -0.09
    tered
    -0.09
    andler
    -0.08
    OPY
    -0.08
    enance
    -0.08
    å¤ļå±Ĥ次
    -0.08
    agli
    -0.08
    æīĢæıIJä¾Ľ
    -0.08
    å¨ĵ
    -0.08
    åķ»
    -0.08
    POSITIVE LOGITS
    iali
    0.11
    wed
    0.10
    åħ¬å¸ĥçļĦ
    0.09
    åĩºç§Ł
    0.09
    igit
    0.09
    berry
    0.09
    ãģ°ãģĭãĤĬ
    0.09
    çijĻ
    0.09
    urious
    0.09
    åĩºåİĤ
    0.09
    Activations Density 0.011%

    No Known Activations