© 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. 9-TRANSCODER-HP
    7. 29702
    Prev
    Next
    INDEX
    Explanations

    Latino

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Indy
    -0.30
     Grove
    -0.30
    ä¸ĸçķĮä¸ĬæľĢ
    -0.27
    à¹Ĩ
    -0.25
    dad
    -0.25
    çĶľ
    -0.25
    Creature
    -0.24
    ['
    -0.24
    éĩįåŀĭ
    -0.24
    rum
    -0.24
    POSITIVE LOGITS
     Soros
    0.28
    actics
    0.27
     fries
    0.26
     obliged
    0.26
    amas
    0.25
    åĬłåĪĨ
    0.25
    çĸ«
    0.25
     mlx
    0.24
    OTOS
    0.24
     millennials
    0.24
    Activations Density 0.686%

    No Known Activations