© 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. 22-TRANSCODER-HP
    7. 87635
    Prev
    Next
    INDEX
    Explanations

    passive voice actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¾¾å°Ķ
    -0.32
    çIJĨæĥ³
    -0.29
    å¢ĥ
    -0.28
    аÑĤоÑĢ
    -0.27
    æĥħåĨµä¸ĭ
    -0.27
    åı¹
    -0.25
     SAM
    -0.24
    红è±Ĩ
    -0.24
     certainly
    -0.24
    ands
    -0.24
    POSITIVE LOGITS
    empor
    0.27
    -columns
    0.26
    faction
    0.25
    beth
    0.24
     Flyers
    0.24
    å¿łå®ŀ
    0.24
    å·¥ä½ľæĬ¥åijĬ
    0.23
     Colleg
    0.23
    idon
    0.23
     privileged
    0.23
    Activations Density 0.029%

    No Known Activations