© 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. 142005
    Prev
    Next
    INDEX
    Explanations

    Anyway

    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
    phy
    -0.30
    ñe
    -0.28
    jal
    -0.26
    thal
    -0.26
    pell
    -0.26
    oidal
    -0.26
     anmeld
    -0.25
     Demp
    -0.25
    ç«Ļéķ¿
    -0.25
    juan
    -0.25
    POSITIVE LOGITS
     IService
    0.31
    ator
    0.28
     turn
    0.28
    转
    0.27
    olia
    0.26
     computing
    0.25
    —or
    0.25
    æķħ
    0.25
    orthy
    0.24
     mol
    0.24
    Activations Density 0.417%

    No Known Activations