© 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. 64289
    Prev
    Next
    INDEX
    Explanations

    Technical documents and news articles

    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
    ably
    -0.33
     purs
    -0.29
    its
    -0.28
    å®ĥçļĦ
    -0.28
    oky
    -0.27
    sist
    -0.27
    amb
    -0.26
    æ»ļ
    -0.26
    p
    -0.25
    å±ŀäºİ
    -0.25
    POSITIVE LOGITS
    iego
    0.27
    è´¦åı·
    0.26
    çĻ½æĸij
    0.25
    å«ĸ
    0.24
    .dest
    0.24
    rypton
    0.24
    ä¿¡ç®±
    0.24
    monds
    0.24
    #",
    0.23
    蹩
    0.23
    Activations Density 3.636%

    No Known Activations