© 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. 46347
    Prev
    Next
    INDEX
    Explanations

    progress and halfway points

    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
    liess
    -0.08
    åIJĮ级
    -0.07
    .swap
    -0.07
    thr
    -0.07
    rove
    -0.06
    åŃ£åĨĽ
    -0.06
    å½ĵå¿ĥ
    -0.06
    ooth
    -0.06
    éŃĶæľ¯å¸Ī
    -0.06
    å°½åı¯èĥ½
    -0.06
    POSITIVE LOGITS
     progress
    0.20
    è¿Ľåº¦
    0.18
     Progress
    0.17
    è¿Ľå±ķ
    0.17
    -progress
    0.17
    progress
    0.16
     progresso
    0.16
    _progress
    0.15
    .Progress
    0.15
    éĢ²åº¦
    0.15
    Activations Density 0.288%

    No Known Activations