© 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. 33-TRANSCODER-HP
    7. 53789
    Prev
    Next
    INDEX
    Explanations

    hy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪĹ
    -0.27
    åĪ©
    -0.26
    elts
    -0.25
    å®°
    -0.25
    iphy
    -0.25
    iams
    -0.25
    ifikasi
    -0.25
    ilver
    -0.25
    isable
    -0.25
     rozwiÄħz
    -0.24
    POSITIVE LOGITS
    .ot
    0.30
    çijķ
    0.28
    èij¡èIJĦ
    0.26
    kul
    0.26
    é»ijé¾Ļ
    0.25
    ä¹ĭä½Ļ
    0.25
    pers
    0.25
    onta
    0.24
    Pack
    0.24
    éĢļè¡Įè¯ģ
    0.24
    Activations Density 0.006%

    No Known Activations