© 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. 26678
    Prev
    Next
    INDEX
    Explanations

    money, cash, liquid, liquidity

    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
    _IMPL
    -0.09
    sky
    -0.09
    agas
    -0.09
    æĢĻ
    -0.09
    sher
    -0.09
    immer
    -0.08
     Pf
    -0.08
     Morm
    -0.08
     Zombies
    -0.08
    å¾Īæĺİæĺ¾
    -0.08
    POSITIVE LOGITS
    åıĺçİ°
    0.12
     cash
    0.11
    çİ°éĩijæµģ
    0.11
    çªģå¦Ĥåħ¶
    0.10
    æµģåĬ¨æĢ§
    0.10
    èĦĨ
    0.10
    çİ°éĩij
    0.10
    èµĦéĩij
    0.10
    对èĩªå·±
    0.10
     liquidity
    0.10
    Activations Density 0.017%

    No Known Activations