© 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. 27-TRANSCODER-HP
    7. 8121
    Prev
    Next
    INDEX
    Explanations

    Casual conversations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹ©çĤ¹
    -0.35
     soon
    -0.35
     quickly
    -0.31
     early
    -0.29
    soon
    -0.28
     sooner
    -0.28
     imminent
    -0.27
    æŶåĪ»
    -0.26
     früh
    -0.26
    early
    -0.25
    POSITIVE LOGITS
    å®ĥåı¯ä»¥
    0.26
    Ñģов
    0.25
    åı¯
    0.25
    æľ¬ç½ij
    0.25
     ØŃÙĪ
    0.25
    ONO
    0.24
    #{@
    0.23
    endant
    0.23
    åĨħåľ°
    0.23
     par
    0.23
    Activations Density 0.006%

    No Known Activations