© 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. 150612
    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
     Stub
    -0.29
     movements
    -0.27
    为大家
    -0.27
    Stub
    -0.26
    èµĺ
    -0.24
    è§Ħ模æľĢ大
    -0.24
    jian
    -0.23
    èij¡èIJĦ
    -0.23
    jie
    -0.23
    ãĥĥãĥĦ
    -0.23
    POSITIVE LOGITS
     impro
    0.29
    CompatActivity
    0.26
    erequisite
    0.25
     getS
    0.24
    åIJ¦
    0.24
    whether
    0.24
    ä¹Łåľ¨
    0.24
     pits
    0.24
    åĵŁ
    0.23
    ç´łè´¨æķĻèĤ²
    0.23
    Activations Density 2.205%

    No Known Activations

    This feature has no known activations.