© 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. 61607
    Prev
    Next
    INDEX
    Explanations

    explicit use of words

    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
    ale
    -0.09
    çĮĬ
    -0.09
    umb
    -0.09
     sinking
    -0.09
    edException
    -0.09
    ãĥĥãĤ¯
    -0.08
    untime
    -0.08
    ousse
    -0.08
    thic
    -0.08
    ingly
    -0.08
    POSITIVE LOGITS
    -minded
    0.13
    ely
    0.13
    ELY
    0.11
    ness
    0.10
    ities
    0.10
    åľ°è¯´
    0.10
    ly
    0.10
    iment
    0.09
    íŀĪ
    0.09
     minded
    0.09
    Activations Density 0.012%

    No Known Activations