© 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. 19-TRANSCODER-HP
    7. 6467
    Prev
    Next
    INDEX
    Explanations

    Bible

    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
    (IDC
    -0.25
    owel
    -0.25
     continent
    -0.25
    dc
    -0.24
    骨æŀ¶
    -0.24
    zzle
    -0.24
    de
    -0.24
    JKLMNOP
    -0.23
    orde
    -0.23
    :///
    -0.23
    POSITIVE LOGITS
    yas
    0.28
    åħ¸
    0.28
    yar
    0.27
    å·¨æĺŁ
    0.26
    éĺģ
    0.26
    hä
    0.25
    TV
    0.25
    nip
    0.25
     symbol
    0.25
    符åı·
    0.24
    Activations Density 0.407%

    No Known Activations