© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51325
    Prev
    Next
    INDEX
    Explanations

    reminiscent or similar to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¨ĺ
    -0.07
    eger
    -0.07
    å°±æĺ¯è¿Ļä¹Ī
    -0.07
    祺
    -0.07
    éĥ½æľīåħ¶
    -0.07
    ocard
    -0.06
     DeepCopy
    -0.06
    idium
    -0.06
    zak
    -0.06
    çªĹåīį
    -0.06
    POSITIVE LOGITS
    è¿ĻæŃ£æĺ¯
    0.13
     reminiscent
    0.12
    åħ¸åŀĭçļĦ
    0.11
    类似äºİ
    0.11
    è¿Ļ让æĪij
    0.10
     resembles
    0.10
    æľīçĤ¹åĥı
    0.10
     resemble
    0.10
     resembled
    0.09
    å¾Īåĥı
    0.09
    Activations Density 0.075%

    No Known Activations