© 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. 14-TRANSCODER-HP
    7. 40592
    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_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adoras
    -0.28
     heck
    -0.28
    egers
    -0.27
    å°Ķæĸ¯
    -0.25
    enstein
    -0.25
    ]+\
    -0.25
    uilt
    -0.25
    ãģĦãģļ
    -0.24
    anism
    -0.24
    _acquire
    -0.24
    POSITIVE LOGITS
     Dialogue
    0.27
    ÑĤем
    0.26
     ok
    0.25
    metadata
    0.24
     occupancy
    0.24
    icky
    0.23
     retreated
    0.23
     aux
    0.23
    èĭĶ
    0.23
    LEV
    0.23
    Activations Density 1.722%

    No Known Activations