© 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. 18224
    Prev
    Next
    INDEX
    Explanations

    passage of time and progression

    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
    æ¿ij
    -0.11
    è¶ģ
    -0.10
    éĢģä¸Ĭ
    -0.10
    .StatusCode
    -0.09
    åħ¥å¸Ĥ
    -0.09
    çģ«çĥ§
    -0.09
    éĥ¨éĥ¨éķ¿
    -0.09
    åĨĴ
    -0.09
    人æĢ§
    -0.08
    象
    -0.08
    POSITIVE LOGITS
    ugal
    0.09
     Neu
    0.08
     Beds
    0.08
    adar
    0.08
     cÃłng
    0.08
    ural
    0.08
    SSF
    0.08
    æĥ°
    0.08
    è¿Ľåħ¥åĪ°
    0.08
    å·¥æľŁ
    0.08
    Activations Density 0.023%

    No Known Activations