© 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. 40010
    Prev
    Next
    INDEX
    Explanations

    false positive, false dawn, false dichotomy, false hope

    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
    lc
    -0.09
    thic
    -0.09
    lasting
    -0.09
    ello
    -0.09
    dsa
    -0.08
    çī¹æ®Ĭ
    -0.08
    ÑģÑĭ
    -0.08
    ually
    -0.08
    abit
    -0.08
    sets
    -0.08
    POSITIVE LOGITS
    wares
    0.12
    hood
    0.11
    æĪŁ
    0.10
    eners
    0.10
    ulence
    0.10
    磾
    0.10
    æ³»
    0.09
    rophe
    0.09
    ãģ¾ãģ¾
    0.09
    ivec
    0.09
    Activations Density 0.036%

    No Known Activations