© 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. 31518
    Prev
    Next
    INDEX
    Explanations

    fierce or vicious intensity

    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
    ting
    -0.12
    son
    -0.10
    ton
    -0.10
    ts
    -0.09
    rab
    -0.09
    ol
    -0.09
    å°Ķ
    -0.08
    v
    -0.08
    uration
    -0.08
    vs
    -0.08
    POSITIVE LOGITS
    ened
    0.14
    NESS
    0.13
    对å¾ħ
    0.13
    -looking
    0.12
    fully
    0.12
    ement
    0.11
    emente
    0.11
    iously
    0.11
    loom
    0.11
    èĨº
    0.11
    Activations Density 0.003%

    No Known Activations