© 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. 18-TRANSCODER-HP
    7. 89395
    Prev
    Next
    INDEX
    Explanations

    technical documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isu
    -0.31
     inflamm
    -0.28
    allo
    -0.27
    ĮĢ
    -0.25
     ör
    -0.25
    onto
    -0.24
     ENT
    -0.24
     Intelli
    -0.24
    omite
    -0.24
    imizer
    -0.23
    POSITIVE LOGITS
     deepest
    0.26
    aya
    0.26
     cours
    0.26
    ìłľ
    0.26
    _nm
    0.26
    ::
    0.26
    \Extension
    0.25
    adem
    0.24
    Expanded
    0.24
    æ·±
    0.24
    Activations Density 21.953%

    No Known Activations