© 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. 50187
    Prev
    Next
    INDEX
    Explanations

    "Hmm" or "mmm" followed by agreement or elaboration

    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
    ivec
    -0.08
    رار
    -0.08
    arra
    -0.08
    otron
    -0.08
    egram
    -0.08
    mainen
    -0.08
    .Reverse
    -0.08
    ppone
    -0.08
    Ïīν
    -0.08
    heck
    -0.08
    POSITIVE LOGITS
    å«ī
    0.07
     dis
    0.06
     som
    0.06
     tw
    0.06
     tug
    0.06
    fil
    0.06
    -intensive
    0.06
    Fast
    0.06
     output
    0.06
    çĻ½æĹ¥
    0.06
    Activations Density 0.001%

    No Known Activations