© 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. 23-TRANSCODER-HP
    7. 23905
    Prev
    Next
    INDEX
    Explanations

    air

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    repeat
    -0.30
    æ·±åİļçļĦ
    -0.27
     bru
    -0.26
    æ¯ĹéĤ»
    -0.24
     inne
    -0.24
    çIJ¼
    -0.24
    _external
    -0.24
    Century
    -0.24
    .outer
    -0.24
    Repeat
    -0.24
    POSITIVE LOGITS
     haze
    0.28
    ä¸ĢåIJį
    0.26
    aire
    0.26
     air
    0.26
    åºŁæ°Ķ
    0.25
    gue
    0.25
     Taipei
    0.25
    亮度
    0.24
    pha
    0.24
    uple
    0.24
    Activations Density 0.007%

    No Known Activations