© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161890
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æī¼
    -0.28
     COLL
    -0.27
     rather
    -0.27
    éĢ»è¾ij
    -0.26
    leted
    -0.26
    planation
    -0.25
    )...
    -0.25
    ãĤĪãģŃ
    -0.25
    æľĹ
    -0.25
    sworth
    -0.25
    POSITIVE LOGITS
    bnb
    0.28
    .keep
    0.26
    -help
    0.24
    maal
    0.24
    fon
    0.24
    dv
    0.23
    ders
    0.23
     Yak
    0.23
    UIApplication
    0.23
    åĢļ
    0.23
    Activations Density 0.828%

    No Known Activations