© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7043
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¸ĥ
    -0.29
    gettext
    -0.27
    cis
    -0.25
    åľŃ
    -0.25
    aho
    -0.25
    æĭīä¸ģ
    -0.25
    .assertThat
    -0.24
    \Auth
    -0.24
    åĬĽéĩı
    -0.24
    å¯Ĩ
    -0.24
    POSITIVE LOGITS
    åIJĽ
    0.30
     Madd
    0.27
     ÑĢазв
    0.27
    odb
    0.26
    æľīå¤ļ大
    0.26
     synchron
    0.26
     Consort
    0.25
    âĨ©
    0.23
    ationToken
    0.23
    emb
    0.23
    Activations Density 1.039%

    No Known Activations

    This feature has no known activations.