© 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. 13372
    Prev
    Next
    INDEX
    Explanations

    United States geography

    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
    acol
    -0.08
    apat
    -0.07
    alon
    -0.07
    akt
    -0.07
    ÃŃst
    -0.07
    ahi
    -0.07
    å§
    -0.07
    θά
    -0.06
    alas
    -0.06
    æĶ¶éŁ³
    -0.06
    POSITIVE LOGITS
     plus
    0.14
     except
    0.12
    åĬłä¸Ĭ
    0.12
    plus
    0.12
    except
    0.11
     плÑİÑģ
    0.11
    åĨįåĬłä¸Ĭ
    0.11
    _except
    0.10
    éĻ¤
    0.10
     Plus
    0.10
    Activations Density 0.270%

    No Known Activations