© 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. 64008
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    chter
    -0.32
    olta
    -0.30
    ubar
    -0.25
    é³ŀ
    -0.24
    andles
    -0.24
    ainty
    -0.24
    ç¯ĵ
    -0.24
     Inst
    -0.24
    _again
    -0.24
    ijľ
    -0.23
    POSITIVE LOGITS
    usto
    0.28
    決
    0.28
    adder
    0.27
    oya
    0.26
    èĩªè´¸
    0.26
    èĩªè§ī
    0.26
    osph
    0.25
    éĢļåħ³
    0.25
    odial
    0.25
    dm
    0.25
    Activations Density 0.401%

    No Known Activations

    This feature has no known activations.