© 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. 130610
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    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
    åħ±åIJĮåıijå±ķ
    -0.28
    ues
    -0.28
    ãģĻãģİãģ¦
    -0.27
    çĿĢ
    -0.25
    æł¡
    -0.25
    ampled
    -0.24
    æ·¡æ·¡
    -0.24
    使åħ¶
    -0.24
    æľīè¿ĩ
    -0.24
    ceu
    -0.23
    POSITIVE LOGITS
    lá
    0.28
     пÑĢедÑĥÑģмоÑĤÑĢ
    0.28
    (Canvas
    0.26
    erset
    0.26
     behold
    0.25
     Investigators
    0.25
    itage
    0.24
    andi
    0.24
     fidelity
    0.23
     setObject
    0.23
    Activations Density 90.631%

    No Known Activations