© 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. 40256
    Prev
    Next
    INDEX
    Explanations

    Numerical data or heights

    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
     Intr
    -0.27
     Amb
    -0.27
    -contrib
    -0.26
    Streaming
    -0.25
    ÑİÑīие
    -0.25
    ElementType
    -0.25
     paths
    -0.25
    jamin
    -0.24
     favorites
    -0.24
     intr
    -0.24
    POSITIVE LOGITS
    飬
    0.28
    IPS
    0.26
    ersive
    0.26
    "profile
    0.24
     juste
    0.24
    çŀ½
    0.24
    éĴ°
    0.23
    åĩĨ
    0.23
    igans
    0.23
    hold
    0.23
    Activations Density 0.842%

    No Known Activations