© 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. 63764
    Prev
    Next
    INDEX
    Explanations

    achievement

    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
    uling
    -0.26
    ä¸ĢåĪĨ
    -0.25
    ular
    -0.25
    isors
    -0.25
    æŃ£
    -0.24
    iteur
    -0.24
    isms
    -0.24
    ÃŃn
    -0.24
    yers
    -0.24
    .BindingSource
    -0.24
    POSITIVE LOGITS
    âķĹ
    0.29
     goal
    0.26
     seeker
    0.24
     tat
    0.24
    FUL
    0.24
     goals
    0.24
    orage
    0.24
    è°ģçŁ¥éģĵ
    0.24
    çģ¿çĥĤ
    0.23
    great
    0.23
    Activations Density 14.466%

    No Known Activations