© 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. 96204
    Prev
    Next
    INDEX
    Explanations

    Code, programming, URLs

    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
    ick
    -0.28
     vag
    -0.28
    ambi
    -0.26
    åĽ°éļ¾
    -0.25
    ourage
    -0.25
     spar
    -0.25
    ä¸įç¦ģ
    -0.25
    istar
    -0.25
    导è´Ń
    -0.24
    æīįç®Ĺ
    -0.24
    POSITIVE LOGITS
    ROWS
    0.28
    aise
    0.28
    .nio
    0.25
    ż
    0.25
    enate
    0.25
    eson
    0.25
     Ñģв
    0.24
     propTypes
    0.24
    otti
    0.23
    æŁĬ
    0.23
    Activations Density 0.001%

    No Known Activations