© 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. 25-TRANSCODER-HP
    7. 108169
    Prev
    Next
    INDEX
    Explanations

    say "years"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TimeSpan
    -0.28
    èĤĺ
    -0.27
     RETURNS
    -0.27
    座ä½į
    -0.27
    å·Ŀ
    -0.26
    éĺ³
    -0.25
    ç»Łè®¡
    -0.24
    社交åªĴä½ĵ
    -0.24
    sequence
    -0.24
    istence
    -0.24
    POSITIVE LOGITS
    ä¿®æŃ£
    0.28
    身ä¸Ĭ
    0.27
    åįģå¹´åīį
    0.27
     shaved
    0.27
    old
    0.25
    ogl
    0.24
    æĮĤåľ¨
    0.24
     olds
    0.24
    hen
    0.24
     old
    0.24
    Activations Density 0.922%

    No Known Activations