© 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. 47753
    Prev
    Next
    INDEX
    Explanations

    herbivore feeding mechanisms

    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
    æ¿ĢåĬ¨
    -0.07
    .catch
    -0.07
    çĶ·åĦ¿
    -0.07
    íķ©
    -0.07
    catch
    -0.07
    åĨ·æ°Ķ
    -0.07
    åħĭéļ¾
    -0.07
    çĩĥ
    -0.07
    ç¾Ķ
    -0.07
    tep
    -0.07
    POSITIVE LOGITS
    饱
    0.09
    åķĥ
    0.09
     nib
    0.08
     indiscrim
    0.08
    _consum
    0.08
    åħī顾
    0.07
     devour
    0.07
     destructive
    0.07
    é£Ł
    0.07
    æľĢçĪ±
    0.07
    Activations Density 0.052%

    No Known Activations