© 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. 19-TRANSCODER-HP
    7. 8603
    Prev
    Next
    INDEX
    Explanations

    trail

    np_max-act · gemini-2.0-flash
    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
    izedName
    -0.27
     Feinstein
    -0.26
    ####↵
    -0.24
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.23
    -ion
    -0.23
    æĿĤè´¨
    -0.23
    onda
    -0.22
    Æ°Æ¡i
    -0.22
    aData
    -0.22
    -floating
    -0.22
    POSITIVE LOGITS
     closely
    0.28
    -making
    0.27
    led
    0.26
    erno
    0.25
    æĦĪ
    0.24
    et
    0.24
     jur
    0.23
     exc
    0.23
    nad
    0.23
    pack
    0.23
    Activations Density 1.213%

    No Known Activations