© 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. 107633
    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
     riv
    -0.30
     Quantity
    -0.29
    ãģĵãģ¡ãĤī
    -0.28
    rens
    -0.27
     quantities
    -0.26
    è¿Ļåĩł
    -0.26
    å²³
    -0.26
     sided
    -0.26
     foreground
    -0.25
     selections
    -0.25
    POSITIVE LOGITS
    bourne
    0.29
    tics
    0.28
    æ¤Ĵ
    0.28
    zza
    0.27
    sterol
    0.25
    abilité
    0.25
    Trail
    0.25
    Advisor
    0.25
    -boot
    0.25
    åĮĸçŁ³
    0.24
    Activations Density 1.092%

    No Known Activations

    This feature has no known activations.