© 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. 88957
    Prev
    Next
    INDEX
    Explanations

    interest

    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
    çŃīåľ°
    -0.26
    .Generated
    -0.25
    ä¸Ģ个éĹ®é¢ĺ
    -0.25
    èµĸ以çĶŁåŃĺ
    -0.25
    ihar
    -0.25
    straint
    -0.24
    ooth
    -0.24
    )))),
    -0.24
    ittest
    -0.23
    thè
    -0.23
    POSITIVE LOGITS
     IMM
    0.25
    emics
    0.24
    /debug
    0.24
     marker
    0.24
    æĻļæľŁ
    0.24
     immune
    0.24
    emin
    0.24
    æ²£
    0.23
    ä¸ĢåĽ¢
    0.23
    immune
    0.23
    Activations Density 23.467%

    No Known Activations