© 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. 1860
    Prev
    Next
    INDEX
    Explanations

    age and life milestones

    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
    pcm
    -0.10
    ç´§å¼ł
    -0.09
    bjerg
    -0.09
    åį§
    -0.09
    éĿł
    -0.09
    è§ij
    -0.09
    Rib
    -0.08
     Rib
    -0.08
    åı¦è¡Į
    -0.08
    ç¹ĩ
    -0.08
    POSITIVE LOGITS
    å¹´é¾Ħ段
    0.18
    å¹´é¾Ħ
    0.17
    年纪
    0.14
     age
    0.13
     tuá»ķi
    0.12
    éĺ¶æ®µ
    0.12
    é¾Ħ
    0.12
    _age
    0.12
     ages
    0.12
    åıijå±ķéĺ¶æ®µ
    0.12
    Activations Density 0.051%

    No Known Activations