© 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. 23-TRANSCODER-HP
    7. 25021
    Prev
    Next
    INDEX
    Explanations

    Lund Lind

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    мÑı
    -0.27
    æ¯Ļ
    -0.25
    é¹ħ
    -0.25
    nestjs
    -0.25
    .databinding
    -0.24
     TestBed
    -0.24
    agnost
    -0.24
    èľ»
    -0.23
    getApplication
    -0.23
    è¿ĻäºĽéĹ®é¢ĺ
    -0.23
    POSITIVE LOGITS
    kop
    0.28
    éħŀ
    0.26
     Combo
    0.26
    licht
    0.25
    ivated
    0.24
    æĿ¯
    0.24
    åĢĴ
    0.24
    æłĭ
    0.24
     drift
    0.23
    comb
    0.23
    Activations Density 0.111%

    No Known Activations