© 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
    2. Qwen3-14B
    3. 20-RESID-BATCHTOPK-65K__L0-80
    4. 13471
    Prev
    Next
    INDEX
    Explanations

    code delimiters and urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [loc
    -0.19
    ledon
    -0.18
    ernational
    -0.17
     ë¬¼ë¡ł
    -0.17
    bine
    -0.16
    åĮĹéĥ¨
    -0.16
    gency
    -0.16
    eger
    -0.16
    .appspot
    -0.16
    enne
    -0.16
    POSITIVE LOGITS
    :]
    0.26
    ...]↵↵
    0.25
    ]
    0.25
    .newaxis
    0.24
    ...]
    0.24
    ].
    0.23
    ]()
    0.23
    ][
    0.22
    _]
    0.22
    ]↵↵
    0.21
    Activations Density 0.869%

    No Known Activations