© 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. 8998
    Prev
    Next
    INDEX
    Explanations

    Social media pages/groups

    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
    heels
    -0.29
    åİļéĩį
    -0.25
    eno
    -0.24
    ench
    -0.24
     tread
    -0.24
    çľģæķĻèĤ²
    -0.23
    wä
    -0.23
    yk
    -0.23
    <J
    -0.23
    rades
    -0.23
    POSITIVE LOGITS
    æģŃ
    0.26
    åĩºåİĤ
    0.26
    å¤ı
    0.25
    çĶ²
    0.25
    uff
    0.25
     Hus
    0.25
     topology
    0.24
    èĩªçĶ±è´¸æĺĵ
    0.23
    stab
    0.23
     addAction
    0.23
    Activations Density 0.017%

    No Known Activations