© 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. 19472
    Prev
    Next
    INDEX
    Explanations

    adjectives ending in -ical, -ological, -ographical

    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
    istic
    -0.09
    ization
    -0.09
    ers
    -0.09
    cape
    -0.09
    ORN
    -0.09
    ator
    -0.09
    à¤
    -0.09
    ine
    -0.09
    åIJ¦
    -0.08
    磬
    -0.08
    POSITIVE LOGITS
    èĭĹ
    0.09
    bine
    0.09
    alone
    0.09
    alo
    0.09
    нал
    0.09
    bsub
    0.09
    缮ãģ«
    0.08
    byn
    0.08
    ç¾½
    0.08
     маÑĤеÑĢиалÑĭ
    0.08
    Activations Density 0.595%

    No Known Activations