© 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. 141121
    Prev
    Next
    INDEX
    Explanations

    names

    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
    ive
    -0.35
    ived
    -0.28
    åĸī
    -0.28
    iw
    -0.28
    memberof
    -0.28
    NodeType
    -0.27
    lifetime
    -0.26
    ivel
    -0.26
    ible
    -0.25
    iveness
    -0.25
    POSITIVE LOGITS
     Oz
    0.26
     Osc
    0.25
     MIL
    0.25
     hatırl
    0.25
     Parts
    0.24
     açıl
    0.24
    ãĤ¹ãĤ¿ãĥ³
    0.24
    Opens
    0.24
     telegram
    0.23
     wherever
    0.23
    Activations Density 5.445%

    No Known Activations