© 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. 24-TRANSCODER-HP
    7. 150166
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rowing
    -0.27
    å½ĵæŶçļĦ
    -0.25
    ((__
    -0.25
    anging
    -0.25
    oug
    -0.25
    aptor
    -0.25
    ained
    -0.25
    ain
    -0.24
    =>'
    -0.24
    .constructor
    -0.23
    POSITIVE LOGITS
     Manufact
    0.27
    çļĦåĪ©çĽĬ
    0.26
     teaser
    0.26
    goog
    0.26
     noses
    0.26
    æĬķæĶ¾
    0.25
    弥漫
    0.25
    \E
    0.25
     manufacture
    0.24
     Ends
    0.24
    Activations Density 0.251%

    No Known Activations

    This feature has no known activations.