© 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. 24347
    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
    趸
    -0.28
     spoken
    -0.28
     transition
    -0.27
     Transition
    -0.27
    éħ¤
    -0.27
    omba
    -0.26
    Transition
    -0.25
     fron
    -0.24
     squ
    -0.24
    éĢıè¿ĩ
    -0.24
    POSITIVE LOGITS
    rts
    0.31
     clearfix
    0.28
     rightly
    0.27
    ernet
    0.26
    æĭİ
    0.26
    astes
    0.26
    æŀŀ
    0.25
     hjem
    0.25
    pit
    0.25
    umbs
    0.24
    Activations Density 0.362%

    No Known Activations

    This feature has no known activations.