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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5760
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    is
    -0.31
    кÑĥп
    -0.29
    cript
    -0.28
    ist
    -0.26
     .
    -0.26
     honor
    -0.25
    ]initWith
    -0.25
    é©°
    -0.25
    zd
    -0.25
    ari
    -0.25
    POSITIVE LOGITS
    第äºĮ次
    0.28
    haps
    0.28
     unnecessarily
    0.26
    åĨįæĿ¥
    0.26
    第ä¸ī次
    0.25
    andum
    0.24
    ç§ĺè¯Ģ
    0.24
     wishes
    0.24
    _interaction
    0.24
     curry
    0.24
    Activations Density 1.360%

    No Known Activations