© 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. 89801
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    pname
    -0.28
    缴æݥ影åĵį
    -0.27
    dp
    -0.26
    çĮľ
    -0.26
    çĪ²
    -0.25
    prove
    -0.25
     sco
    -0.25
    _;↵
    -0.24
    éĿŀ常éĩįè¦ģ
    -0.24
    GN
    -0.24
    POSITIVE LOGITS
    ä¹Łä¸įæķ¢
    0.30
    igest
    0.29
    )const
    0.29
    endon
    0.28
    izu
    0.27
    ecessarily
    0.26
    ä¸įä¸Ĭ
    0.25
    ä¹Łä¸įåı¯èĥ½
    0.24
    isons
    0.24
     Dent
    0.24
    Activations Density 18.163%

    No Known Activations