© 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. 89326
    Prev
    Next
    INDEX
    Explanations

    Code, URLs, and forum content

    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
    entials
    -0.29
    utive
    -0.28
     Ideas
    -0.28
    ideas
    -0.28
    榴
    -0.27
     Fur
    -0.25
    ivities
    -0.25
    iliar
    -0.24
    ousel
    -0.24
    inders
    -0.24
    POSITIVE LOGITS
    çªį
    0.26
     f
    0.26
    .Typed
    0.26
    fällig
    0.24
     complaining
    0.24
     orig
    0.24
     puzzled
    0.24
     fe
    0.23
    ISM
    0.23
    è£ħéħį
    0.23
    Activations Density 1.265%

    No Known Activations