© 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. 23-TRANSCODER-HP
    7. 24878
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERC
    -0.26
    ,:,
    -0.26
    ç¡®ä¿Ŀ
    -0.26
    åħĪ
    -0.26
    èĻ½çĦ¶
    -0.25
     Sens
    -0.25
     Contents
    -0.25
    éĢĴ
    -0.25
    urv
    -0.24
    åIJĦåįķä½į
    -0.24
    POSITIVE LOGITS
    aign
    0.32
    èĤ±
    0.27
    stown
    0.26
    éĤ£æ®µ
    0.26
    ouro
    0.26
     punching
    0.26
    èIJ½
    0.25
     suffice
    0.25
    æ»ŀ
    0.25
     thanking
    0.25
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.