© 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. 31026
    Prev
    Next
    INDEX
    Explanations

    command line terms `type`, `draw()`, `iptables`, `Proof` of

    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
    rastructure
    -0.10
    bidden
    -0.07
    egrated
    -0.07
    standing
    -0.06
    gunakan
    -0.06
    consts
    -0.06
    æĪIJèį¯
    -0.06
    æĸ°æŧ
    -0.06
    guarded
    -0.06
    umped
    -0.06
    POSITIVE LOGITS
    orem
    0.13
    jenigen
    0.10
    olesterol
    0.09
    -Encoding
    0.09
    itage
    0.09
    oretical
    0.09
    -Version
    0.08
    .hs
    0.08
    uristic
    0.08
    -Col
    0.08
    Activations Density 1.807%

    No Known Activations