© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8904
    Prev
    Next
    INDEX
    Explanations

    less fortunate, fundraising, neurotoxicity, hyperplastic

    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
    ฤ
    -0.09
    åIJ¹
    -0.09
    åıĹåĪ°
    -0.08
    èĪªç©º
    -0.08
    åı£å¾Ħ
    -0.08
    èĩªå¦Ĥ
    -0.08
    aths
    -0.08
    communications
    -0.08
    .au
    -0.08
    Neill
    -0.08
    POSITIVE LOGITS
    æķijåĬ©
    0.13
    è´«
    0.12
    æī¶è´«
    0.12
    æķijæµİ
    0.11
    饥饿
    0.11
    帮æī¶
    0.11
    æħĪåĸĦ
    0.11
    窮
    0.10
    貧
    0.10
    åħ¬çĽĬæ´»åĬ¨
    0.10
    Activations Density 0.114%

    No Known Activations