© 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. 88655
    Prev
    Next
    INDEX
    Explanations

    responses and communication

    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
    .Q
    -0.27
    ĸī
    -0.26
     mix
    -0.24
    鸡汤
    -0.24
    ^K
    -0.24
    itag
    -0.24
    Ĥ¤
    -0.24
    trs
    -0.24
    æī¾åĽŀ
    -0.24
    åıĸåĨ³
    -0.23
    POSITIVE LOGITS
    /current
    0.29
    令
    0.27
    phinx
    0.26
     current
    0.26
    SUP
    0.25
    oge
    0.25
    eken
    0.25
     cabo
    0.24
    ä¹ħä¹ħ
    0.24
    (begin
    0.24
    Activations Density 12.413%

    No Known Activations