© 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. 27963
    Prev
    Next
    INDEX
    Explanations

    length, long, longer

    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
    åł¡
    -0.09
    ç§¦åĽ½
    -0.09
    羣å®ŀçļĦ
    -0.09
    åıŁ
    -0.09
    reso
    -0.08
    ä¸ĥåįģ
    -0.08
    éĶ£
    -0.08
    èĢģçĪ·
    -0.08
    _manual
    -0.08
    pta
    -0.08
    POSITIVE LOGITS
    éķ¿çŁŃ
    0.13
    éķ¿åº¦
    0.13
    -length
    0.13
     length
    0.13
     shorter
    0.12
    è¾ĥéķ¿
    0.12
     lengths
    0.11
    éķ¿éķ¿
    0.11
     longer
    0.11
     Length
    0.11
    Activations Density 0.107%

    No Known Activations