© 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. 29778
    Prev
    Next
    INDEX
    Explanations

    bracket and/or c

    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
    æ°Ķ象
    -0.28
    alcon
    -0.27
    iali
    -0.25
    infeld
    -0.25
    ä¼ĺåĮĸ
    -0.25
     spyOn
    -0.24
    ivy
    -0.24
    laughter
    -0.24
    å®ł
    -0.24
    éĻį
    -0.23
    POSITIVE LOGITS
    çĿĢæĢ¥
    0.29
    iggins
    0.26
    ~-
    0.25
    é¢ĺ主
    0.25
    VALUE
    0.25
    å¿ħçĦ¶ä¼ļ
    0.25
    çľ¼çIJĥ
    0.24
    orang
    0.24
    ural
    0.24
    _permalink
    0.23
    Activations Density 2.285%

    No Known Activations