© 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. 25055
    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
    odiac
    -0.30
    IRQ
    -0.25
    _sector
    -0.25
     Choices
    -0.25
    posit
    -0.24
     Listings
    -0.24
    èĪĮ
    -0.24
    ä¹Łä¸į
    -0.24
    _VOL
    -0.24
    tics
    -0.23
    POSITIVE LOGITS
    çĺģ
    0.27
     cljs
    0.26
    çļĦ强大
    0.26
    æ·¬
    0.25
     binder
    0.25
    æĥ°
    0.25
    ?p
    0.24
    ivalence
    0.24
     lid
    0.24
    roduce
    0.24
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.