© 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. 30-TRANSCODER-HP
    7. 96052
    Prev
    Next
    INDEX
    Explanations

    cord

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mellon
    -0.28
    æ¼ı
    -0.28
     earning
    -0.27
    æ§ģ
    -0.25
    _READONLY
    -0.24
     pend
    -0.24
    moid
    -0.24
     saÄŁlam
    -0.24
     Canterbury
    -0.24
     meeting
    -0.23
    POSITIVE LOGITS
    inee
    0.32
    UGE
    0.31
    łģ
    0.31
    å¹´é¾Ħ
    0.27
    age
    0.27
    fox
    0.27
    èIJ
    0.27
    约æĿŁ
    0.26
     AGE
    0.26
    spr
    0.26
    Activations Density 0.883%

    No Known Activations