© 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. 33-TRANSCODER-HP
    7. 53947
    Prev
    Next
    INDEX
    Explanations

    document excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.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´¡çĮ®
    -0.28
    TERS
    -0.27
     pro
    -0.26
    	bl
    -0.24
    çľĭä¸Ģä¸ĭ
    -0.24
    æĿ¡
    -0.24
    layan
    -0.24
    gateway
    -0.23
    erah
    -0.23
    _vote
    -0.23
    POSITIVE LOGITS
    ieri
    0.29
    rek
    0.27
    ardo
    0.27
     Kang
    0.27
    oco
    0.27
    (di
    0.26
    DX
    0.25
    康
    0.25
     pans
    0.25
    itez
    0.25
    Activations Density 0.006%

    No Known Activations