© 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. 29516
    Prev
    Next
    INDEX
    Explanations

    Zeros

    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
    dress
    -0.27
     dress
    -0.27
    çļĦåľ°åĽ¾
    -0.26
     sentence
    -0.25
    çļĦçĪ±æĥħ
    -0.25
    .currentIndex
    -0.25
    homes
    -0.24
    ç»ıéªĮ丰å¯Į
    -0.24
    循çݯ
    -0.23
    .mapping
    -0.23
    POSITIVE LOGITS
    ri
    0.29
    ìŀIJê°Ģ
    0.26
    ahi
    0.26
    ç½²
    0.26
     preds
    0.25
    arten
    0.25
    éĢIJ
    0.25
    uel
    0.25
    ä¸Ļ
    0.24
     dying
    0.24
    Activations Density 1.532%

    No Known Activations