© 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. 149560
    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
    Crow
    -0.25
    ierz
    -0.25
    crow
    -0.25
    /latest
    -0.25
    :.
    -0.24
    atus
    -0.24
    åħ¨åijĺ
    -0.24
    áºŃm
    -0.24
    ustral
    -0.23
    ,.
    -0.23
    POSITIVE LOGITS
    nest
    0.28
    åĢĻéĢī人
    0.27
    niest
    0.26
    è¤Ĭ
    0.26
    æĹłåĬĽ
    0.26
     nest
    0.25
     Nest
    0.24
    åı«æĪij
    0.24
    åľ¨äºİ
    0.24
    åı¦ä¸Ģ个
    0.24
    Activations Density 3.877%

    No Known Activations

    This feature has no known activations.