© 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. 29808
    Prev
    Next
    INDEX
    Explanations

    Technical text snippets

    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
     Wool
    -0.27
    éĴ´
    -0.26
     collateral
    -0.26
    æī«ä¸Ģæī«
    -0.26
    indh
    -0.25
     Wik
    -0.25
    nj
    -0.25
    vester
    -0.24
    èĵ¼
    -0.24
     prive
    -0.24
    POSITIVE LOGITS
    ely
    0.29
    è¯Ń
    0.27
    efa
    0.27
     Gaussian
    0.26
    amon
    0.26
    ELY
    0.25
    ening
    0.25
    ç©Ĩ
    0.25
    shaw
    0.25
    istik
    0.24
    Activations Density 2.178%

    No Known Activations