© 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. Qwen3-4B
    5. 9-TRANSCODER-HP
    7. 29638
    Prev
    Next
    INDEX
    Explanations

    binary code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    undle
    -0.27
    angelo
    -0.26
    oulos
    -0.24
    (DialogInterface
    -0.24
    客
    -0.24
    ники
    -0.24
    ilate
    -0.23
    人ãģĮ
    -0.23
     зак
    -0.23
     Flour
    -0.23
    POSITIVE LOGITS
    没æĶ¶
    0.26
     NSK
    0.26
    fsp
    0.25
    ATAB
    0.25
    Esp
    0.25
    æĺ¶
    0.24
    }s
    0.24
    ä¸Ģä¼ļåĦ¿
    0.24
    adb
    0.24
     BJ
    0.24
    Activations Density 2.757%

    No Known Activations