© 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. 38309
    Prev
    Next
    INDEX
    Explanations

    knockout or knockdown

    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
    ãĥ£
    -0.10
    ality
    -0.10
    ally
    -0.10
    irty
    -0.10
    otta
    -0.09
    对æłĩ
    -0.09
    iro
    -0.09
    æīĭæİĮ
    -0.08
    arend
    -0.08
    aat
    -0.08
    POSITIVE LOGITS
     Knock
    0.10
    erson
    0.10
     knock
    0.10
    rid
    0.09
    alus
    0.09
    ertext
    0.09
    outs
    0.09
    tie
    0.09
     Äijâu
    0.09
     knocks
    0.09
    Activations Density 0.003%

    No Known Activations