© 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. 141771
    Prev
    Next
    INDEX
    Explanations

    Expressing opinions/indications

    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
     harmony
    -0.26
     validations
    -0.25
     inv
    -0.25
    REW
    -0.25
     washer
    -0.25
    quisa
    -0.24
    Dict
    -0.24
    apter
    -0.24
    .hover
    -0.24
     furthermore
    -0.24
    POSITIVE LOGITS
    tent
    0.35
    _accessible
    0.28
    etro
    0.26
    commit
    0.26
    cover
    0.25
    翻身
    0.25
    åįł
    0.24
     competing
    0.24
    ett
    0.24
    IMO
    0.24
    Activations Density 55.761%

    No Known Activations