© 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. 35-TRANSCODER-HP
    7. 39423
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erce
    -0.26
     cú
    -0.25
    inan
    -0.25
    INAL
    -0.25
    .copy
    -0.25
    nage
    -0.25
    inar
    -0.25
    éĻħ
    -0.24
    ovan
    -0.24
     ÑģÑĥ
    -0.24
    POSITIVE LOGITS
    roc
    0.30
    åĴ§
    0.27
    koneksi
    0.26
    \Foundation
    0.26
     notoriously
    0.25
    .serializer
    0.24
    æĿª
    0.24
    éĥ¨ä¸»ä»»
    0.24
    oston
    0.23
    sitemap
    0.23
    Activations Density 8.578%

    No Known Activations

    This feature has no known activations.