© 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. 96284
    Prev
    Next
    INDEX
    Explanations

    Instinct, intellect, reflexes

    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
    è¿Ľåĩº
    -0.31
    ocup
    -0.31
    åı·çłģ
    -0.26
     setC
    -0.25
    åĩºåħ·
    -0.24
     Saints
    -0.24
    ExecutionContext
    -0.23
     cancellationToken
    -0.23
     Rosen
    -0.23
    åı¯çĸij
    -0.23
    POSITIVE LOGITS
    es
    0.36
    ive
    0.34
    u
    0.32
    ual
    0.30
    o
    0.29
    uela
    0.28
     reflex
    0.28
    uat
    0.28
     for
    0.28
    s
    0.27
    Activations Density 0.796%

    No Known Activations