© 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. 4-TRANSCODER-HP
    7. 107
    Prev
    Next
    INDEX
    Explanations

    database transactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    享æľī
    -0.27
    TINGS
    -0.26
    -face
    -0.26
    çļĦè·Ŀ离
    -0.25
    RelativeTo
    -0.25
     ÑĦай
    -0.25
    wald
    -0.25
     ComVisible
    -0.24
    éĿ¢
    -0.24
     Rosen
    -0.24
    POSITIVE LOGITS
     keyed
    0.28
    asty
    0.26
    åħ¶éĹ´
    0.25
    é©·
    0.25
     Kis
    0.25
     swear
    0.25
     tender
    0.25
    \param
    0.24
    ear
    0.24
    æ¿ŀ
    0.24
    Activations Density 2.678%

    No Known Activations