© 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. 22-TRANSCODER-HP
    7. 130453
    Prev
    Next
    INDEX
    Explanations

    Prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ockey
    -0.28
    ç¼Ŀ
    -0.27
    å®ŀçĶ¨
    -0.26
    ä¸Ńè¶ħ
    -0.26
     About
    -0.25
    odon
    -0.25
    onaut
    -0.25
    å°ıæŶåĨħ
    -0.24
    .ToUpper
    -0.24
    oking
    -0.24
    POSITIVE LOGITS
    shed
    0.25
    åIJĦè¡Į
    0.25
     affirmation
    0.24
    _entities
    0.24
    urf
    0.24
    hä
    0.24
    对çŃĸ
    0.24
    èĪĨ论
    0.24
    iasi
    0.24
    é¦ĸä½į
    0.23
    Activations Density 0.003%

    No Known Activations