© 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. 4916
    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_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¨
    -0.25
    导
    -0.25
    å¤ĩæ¡Ī
    -0.24
    lte
    -0.24
    bere
    -0.24
    afil
    -0.24
    ä¸ŀ
    -0.23
     Eur
    -0.23
    è´°
    -0.23
    大åĬĽ
    -0.23
    POSITIVE LOGITS
    使æĪij
    0.30
     sociology
    0.27
     Beh
    0.26
    æĬĬæĪij
    0.26
    _statuses
    0.25
     ImmutableList
    0.25
    éŁŃ
    0.24
    strncmp
    0.24
    asurable
    0.24
    ç§ģãģĮ
    0.24
    Activations Density 0.213%

    No Known Activations