© 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. 88793
    Prev
    Next
    INDEX
    Explanations

    than

    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
     Outline
    -0.26
     atleast
    -0.25
    TRL
    -0.25
     _|
    -0.24
     Pru
    -0.24
    SJ
    -0.24
    /pp
    -0.24
    SetName
    -0.24
    _|
    -0.24
    /ros
    -0.24
    POSITIVE LOGITS
    :↵
    0.30
    俺
    0.28
    çİ°å®ŀ
    0.26
     prepend
    0.26
    åĴ±
    0.25
    s
    0.25
    æµĵéĥģ
    0.25
    ï¼ļ↵
    0.24
    hat
    0.24
    å´ĩé«ĺ
    0.24
    Activations Density 11.078%

    No Known Activations