© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23283
    Prev
    Next
    INDEX
    Explanations

    mutant, mutation, knockout, deficiency

    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
    è¾¾åħĭ
    -0.07
     Connected
    -0.07
     terrestrial
    -0.06
    ç¿¡
    -0.06
    åŃļ
    -0.06
    çŤ
    -0.06
    ç¾Į
    -0.06
     connected
    -0.06
     fr
    -0.06
    èıģ
    -0.06
    POSITIVE LOGITS
     mutants
    0.13
    缺éĻ·
    0.12
    æĹłæ³ķæŃ£å¸¸
    0.12
     mutant
    0.11
     defective
    0.11
     variants
    0.11
    éģĹä¼ł
    0.10
     mutations
    0.10
     mutation
    0.10
    çªģåıĺ
    0.10
    Activations Density 0.303%

    No Known Activations