© 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. 22-TRANSCODER-HP
    7. 112288
    Prev
    Next
    INDEX
    Explanations

    Railroads, roads, plantations, reservations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erno
    -0.26
    åijĽ
    -0.26
    åħ¬å¼ĢèµĽ
    -0.25
    ÑĪин
    -0.23
     sino
    -0.23
     trio
    -0.23
    殿åłĤ
    -0.23
    åħį
    -0.23
    _brand
    -0.23
    客åİħ
    -0.23
    POSITIVE LOGITS
     dollars
    0.25
    ually
    0.25
     ALERT
    0.25
    doll
    0.25
     towers
    0.24
    è§Ħ
    0.24
    CTL
    0.24
    elige
    0.24
    ики
    0.24
    ucher
    0.23
    Activations Density 0.019%

    No Known Activations