© 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. 22301
    Prev
    Next
    INDEX
    Explanations

    feeling states

    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
    eur
    -0.12
    imal
    -0.10
    ely
    -0.10
    bing
    -0.10
    ester
    -0.09
    el
    -0.09
    ç
    -0.09
    -minded
    -0.09
    yard
    -0.09
    ya
    -0.09
    POSITIVE LOGITS
    lessly
    0.13
    ably
    0.12
    æľīå¿ħè¦ģ
    0.11
    ances
    0.11
    -good
    0.10
    èĨº
    0.10
    istic
    0.10
    igy
    0.10
    ance
    0.09
    æĬ±æŃī
    0.09
    Activations Density 0.033%

    No Known Activations