© 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. 4961
    Prev
    Next
    INDEX
    Explanations

    computer-related information

    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
    pmat
    -0.27
    åħ¶å®ĥéĹ®é¢ĺ
    -0.25
    chten
    -0.24
    olk
    -0.24
     Dis
    -0.24
    atives
    -0.24
     FXMLLoader
    -0.23
    akte
    -0.23
    æ·Į
    -0.23
     dis
    -0.23
    POSITIVE LOGITS
     facto
    0.25
    worthy
    0.25
    "—
    0.23
    ,var
    0.23
    purpose
    0.23
    ç¬ijç¬ij
    0.23
    ä¸ĢçĤ¹
    0.23
    ROUGH
    0.22
     Hemisphere
    0.22
    IN
    0.22
    Activations Density 0.123%

    No Known Activations