© 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. 130349
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    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
    ustin
    -0.28
    etroit
    -0.27
    ake
    -0.27
    楫
    -0.26
    lane
    -0.25
    MAKE
    -0.25
    shaw
    -0.24
     Trafford
    -0.24
     '*.
    -0.24
    åºļ
    -0.24
    POSITIVE LOGITS
    ?page
    0.29
    /rs
    0.27
    _mut
    0.27
    erais
    0.26
    以åıĬ
    0.26
    adians
    0.26
     st
    0.26
    Mut
    0.26
    æĶ¾
    0.26
     sym
    0.26
    Activations Density 52.782%

    No Known Activations