© 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. 20-TRANSCODER-HP
    7. 130613
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èIJ¥éĢł
    -0.26
     hard
    -0.26
    åĽ¢éĺŁ
    -0.25
    team
    -0.25
    andro
    -0.24
    çħ§é¡¾
    -0.24
    çľĭ
    -0.24
    èĭį
    -0.24
    æ±Łæ¹ĸ
    -0.24
    太太
    -0.23
    POSITIVE LOGITS
    æ¯ħ
    0.28
    elsius
    0.27
    è§
    0.25
    ä»įæľª
    0.25
     #__
    0.25
    (#)
    0.25
    èķ¾
    0.25
    shr
    0.24
    ORLD
    0.24
    igung
    0.24
    Activations Density 11.464%

    No Known Activations