© 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
    2. Qwen3-1.7B
    3. 27-LLAMASCOPE-2-LORSA-16K-K64
    4. 14845
    Prev
    Next
    INDEX
    Explanations

    say "newline punctuation"

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tps
    -19.75
    OCI
    -19.00
     zb
    -18.00
    (tp
    -17.63
    TU
    -17.13
    avra
    -17.13
    (ct
    -17.13
     TPM
    -16.75
    BLE
    -16.75
    PLY
    -16.75
    POSITIVE LOGITS
    }
    ↵
    13.88
     fluid
    13.06
    )
    ↵
    13.06
    )
    ↵
    13.00
    }>
    ↵
    13.00
    .netflix
    12.31
    )
    ↵
    ↵
    12.06
    }
    ↵
    ↵
    12.00
    ),
    ↵
    12.00
    },
    ↵
    11.94
    Activations Density 0.432%

    No Known Activations