© 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. 57988
    Prev
    Next
    INDEX
    Explanations

    mitochondrial DNA mutations

    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
    esses
    -0.08
    æ³½
    -0.08
    <|box_end|>
    -0.07
    åħ¶æŀĹ
    -0.07
     gespre
    -0.07
    seh
    -0.07
    ellate
    -0.07
    è§Ħ模以ä¸Ĭ
    -0.07
     convertible
    -0.07
    Normals
    -0.07
    POSITIVE LOGITS
    -only
    0.07
    èĥİ
    0.07
    ernal
    0.07
     matern
    0.07
     mitochondrial
    0.07
     pig
    0.07
    ieg
    0.06
    DNA
    0.06
     inherited
    0.06
    uter
    0.06
    Activations Density 0.016%

    No Known Activations