© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6824
    Prev
    Next
    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #error
    -0.29
    :error
    -0.26
    è¿ĻäºĽéĹ®é¢ĺ
    -0.24
    %A
    -0.24
    éºĵ
    -0.24
    身ä½ĵ
    -0.23
    æĶ¹æŃ£
    -0.23
    身躯
    -0.23
    éĻIJæľŁ
    -0.23
    åįģåħ«æĿ¡
    -0.23
    POSITIVE LOGITS
    ogle
    0.33
    rod
    0.26
    åijĺ
    0.26
    wij
    0.25
    注
    0.24
    strom
    0.24
    che
    0.24
    LIB
    0.24
    my
    0.24
     rac
    0.24
    Activations Density 0.048%

    No Known Activations