© 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. 129379
    Prev
    Next
    INDEX
    Explanations

    Legal/official statements

    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
    ibri
    -0.29
    tif
    -0.27
    alli
    -0.26
    LBL
    -0.25
    ERGE
    -0.25
    walker
    -0.24
    ollections
    -0.24
    npc
    -0.24
     "@/
    -0.24
    aspers
    -0.24
    POSITIVE LOGITS
    æ»ļçIJĥ
    0.29
    å°ģéĹŃ
    0.28
    emies
    0.27
    INY
    0.26
    tries
    0.25
    stood
    0.24
    çĿ¢
    0.24
    溢价
    0.24
    ZZ
    0.24
    SMART
    0.24
    Activations Density 12.667%

    No Known Activations