© 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. 107699
    Prev
    Next
    INDEX
    Explanations

    Mechanical/technical components/processes

    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
    è¿ĺæľīä¸Ģ个
    -0.32
    ä¸įèµ·
    -0.30
    MDB
    -0.26
    imat
    -0.26
    ilarity
    -0.26
    åĬ¬
    -0.25
    -rock
    -0.25
    awesome
    -0.25
    loh
    -0.24
    åĽłä¸ºä»ĸ
    -0.24
    POSITIVE LOGITS
    çļĦå¿ĥ
    0.28
    æĭĵ
    0.27
    触
    0.27
    å¿ĥ
    0.26
     candidate
    0.26
     Candidate
    0.26
     candid
    0.25
     heart
    0.25
    иÑĢ
    0.25
    çµIJ
    0.25
    Activations Density 30.439%

    No Known Activations