© 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. 5752
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æݥ触åĪ°
    -0.28
    OR
    -0.28
     OR
    -0.27
     dot
    -0.25
    çĶµ
    -0.24
    utom
    -0.24
    æĭį
    -0.24
    eworld
    -0.24
    _until
    -0.23
    .asp
    -0.23
    POSITIVE LOGITS
    ilon
    0.29
    nds
    0.26
     ÑģиÑĤ
    0.26
    .writeString
    0.26
    MSN
    0.25
    okes
    0.24
     Lazar
    0.24
    èĩ´
    0.24
    ensen
    0.24
    kowski
    0.24
    Activations Density 0.012%

    No Known Activations