© 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. 64514
    Prev
    Next
    INDEX
    Explanations

    IP address assignment

    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
     lod
    -0.07
    acro
    -0.07
     Occ
    -0.07
    åħ·ä½ĵæŶéĹ´
    -0.06
    biet
    -0.06
     spu
    -0.06
    åŃIJç±»
    -0.06
    Occurred
    -0.06
    å®Ŀå±±
    -0.06
    orst
    -0.06
    POSITIVE LOGITS
    assigned
    0.09
    åĪĨéħį
    0.09
     assigned
    0.09
    _allocate
    0.08
    Assigned
    0.08
    åĪĨéħįçļĦ
    0.08
     scheme
    0.08
     schemes
    0.08
     Assigned
    0.08
    irtual
    0.08
    Activations Density 0.044%

    No Known Activations