© 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. 22-TRANSCODER-HP
    7. 98457
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĺĽ
    -0.26
    pective
    -0.26
    gang
    -0.25
    ection
    -0.24
     pref
    -0.24
    éĢıè§Ĩ
    -0.24
    äºĭåıij
    -0.24
    .addData
    -0.23
     ability
    -0.23
     trÆ°Æ¡ng
    -0.22
    POSITIVE LOGITS
    ament
    0.29
    onto
    0.26
    æĿĢ
    0.25
     StyleSheet
    0.25
    cock
    0.25
    ORA
    0.24
    æĥľ
    0.24
    ä¸įå¤Ł
    0.24
    人为
    0.24
    ]|[
    0.24
    Activations Density 0.794%

    No Known Activations

    This feature has no known activations.