© 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. 8375
    Prev
    Next
    INDEX
    Explanations

    scientific/mathematical analysis

    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
    æĭī
    -0.28
    yl
    -0.27
    åıĸå¾Ĺ
    -0.27
    ERR
    -0.26
    ç£ħ
    -0.25
    err
    -0.25
    åĸ¾
    -0.24
    олÑı
    -0.24
    ä¹Ļ
    -0.24
    ãĢĬ
    -0.24
    POSITIVE LOGITS
     computational
    0.35
     conject
    0.35
     phenomen
    0.35
     simpl
    0.32
     computation
    0.32
    èĴ»
    0.31
     symmetry
    0.31
     symmetric
    0.29
     heuristic
    0.29
     intuition
    0.29
    Activations Density 0.006%

    No Known Activations