© 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. 12-TRANSCODER-HP
    7. 22940
    Prev
    Next
    INDEX
    Explanations

    system integration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    屯
    -0.32
    欤
    -0.28
    åĭĴ
    -0.28
     mal
    -0.27
    rie
    -0.27
    梧
    -0.26
    continental
    -0.26
    款
    -0.25
     unde
    -0.25
    次
    -0.25
    POSITIVE LOGITS
    óż
    0.28
    æĹ©æĻļ
    0.28
    pron
    0.28
    IVITY
    0.26
    ä¼ļéķ¿
    0.25
    -spe
    0.25
    Spe
    0.25
    }s
    0.25
     yours
    0.24
     Speaker
    0.24
    Activations Density 0.002%

    No Known Activations