© 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. 25-TRANSCODER-HP
    7. 108997
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inned
    -0.27
    ãģ»ãģ©
    -0.25
    argc
    -0.23
    IDD
    -0.23
    æĺĤ
    -0.23
    å¸®ä½ł
    -0.23
    å®Ĺ
    -0.23
     disproportion
    -0.23
    anything
    -0.23
     drip
    -0.22
    POSITIVE LOGITS
    åĨĻä¸ĭ
    0.30
    bij
    0.27
    orer
    0.27
    åį°
    0.24
    à¸ļà¸Ĺ
    0.24
     Gateway
    0.24
     asc
    0.24
     indict
    0.23
    è¿Ľ
    0.23
    meld
    0.23
    Activations Density 0.113%

    No Known Activations

    This feature has no known activations.