© 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. 40251
    Prev
    Next
    INDEX
    Explanations

    blood circulation

    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
    ulum
    -0.29
    éĻĦå±ŀ
    -0.28
    __$
    -0.27
    å·¥èīº
    -0.26
     Bal
    -0.26
     bud
    -0.26
    cec
    -0.25
    èĶij
    -0.25
    -pattern
    -0.25
     piping
    -0.25
    POSITIVE LOGITS
     fragmented
    0.26
    å²ģ以ä¸Ĭ
    0.26
    aits
    0.25
    [ip
    0.25
    frag
    0.25
     Zionist
    0.25
    .tf
    0.24
    Peace
    0.24
    ÑĢаÐ
    0.24
     Capitals
    0.23
    Activations Density 1.287%

    No Known Activations