© 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. 62804
    Prev
    Next
    INDEX
    Explanations

    adjective suffixes

    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
    ç±»åŀĭçļĦ
    -0.09
    åĥ§
    -0.08
    0
    -0.08
    ocre
    -0.08
    oret
    -0.08
    ched
    -0.08
    çĭĻ
    -0.08
    ological
    -0.08
    9
    -0.08
    4
    -0.08
    POSITIVE LOGITS
    ness
    0.16
    NESS
    0.15
    ä¹ĭåĬ¿
    0.13
    ä¹ĭ举
    0.11
    eness
    0.11
    nes
    0.10
    ä¹ĭå¤Ħ
    0.10
    iveness
    0.10
    etry
    0.10
    thood
    0.10
    Activations Density 0.662%

    No Known Activations