© 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. 107539
    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
    xEB
    -0.32
     oval
    -0.28
     Oxygen
    -0.27
     invers
    -0.27
     inverted
    -0.27
    enes
    -0.27
    ENDOR
    -0.26
     scram
    -0.25
    Eb
    -0.25
    IRST
    -0.25
    POSITIVE LOGITS
    -economic
    0.30
    ipline
    0.29
    豪
    0.28
    ibold
    0.28
    究
    0.27
    å®īæħ°
    0.27
    缮çļĦ
    0.26
    æīĢåģļçļĦ
    0.26
     summaries
    0.26
    termination
    0.26
    Activations Density 1.033%

    No Known Activations

    This feature has no known activations.