© 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. 63219
    Prev
    Next
    INDEX
    Explanations

    geometry shapes

    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
    éĺ´å½±
    -0.27
    注å®ļ
    -0.26
    cline
    -0.25
    shadow
    -0.25
    _COMPARE
    -0.24
     niá»ĩm
    -0.24
    (compare
    -0.24
    å±ķæľĽ
    -0.24
    åĨħ容ç®Ģä»ĭ
    -0.24
    asin
    -0.23
    POSITIVE LOGITS
     Ecc
    0.27
    ously
    0.27
    &oacute
    0.26
    anded
    0.26
    cing
    0.26
    oding
    0.26
    inging
    0.25
     followed
    0.25
     Scientific
    0.25
    oux
    0.24
    Activations Density 7.342%

    No Known Activations