© 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. 23019
    Prev
    Next
    INDEX
    Explanations

    inclined surface or movement

    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
     circulating
    -0.08
    çī¢
    -0.08
    ç¹°
    -0.08
     Klos
    -0.08
    blob
    -0.07
    åľĪåŃIJ
    -0.07
    çĩ
    -0.07
    æįħ
    -0.07
    Ïĩαν
    -0.07
    æµ·ä¸ľ
    -0.07
    POSITIVE LOGITS
    åĿ¡åº¦
    0.15
     slope
    0.13
    åĿ¡
    0.12
     slopes
    0.11
    slope
    0.11
    éĻ¡å³Ń
    0.11
    ç¼ĵ
    0.10
     incl
    0.10
    éĻ¡
    0.10
     steep
    0.10
    Activations Density 0.029%

    No Known Activations