© 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. 30-TRANSCODER-HP
    7. 95709
    Prev
    Next
    INDEX
    Explanations

    destruct

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ion
    -1.27
    ions
    -1.23
    ION
    -1.13
     ion
    -1.02
    ional
    -1.00
    iones
    -0.94
    iona
    -0.94
    离åŃIJ
    -0.94
    IONS
    -0.93
    ione
    -0.93
    POSITIVE LOGITS
    ORK
    0.28
    \Component
    0.26
    rase
    0.25
     maid
    0.25
    åįģåĽĽæĿ¡
    0.24
     lite
    0.24
    achi
    0.23
     Rach
    0.23
    ç»ıæµİåѦ
    0.23
    ILD
    0.23
    Activations Density 0.913%

    No Known Activations