© 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. 18-TRANSCODER-HP
    7. 88594
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arro
    -0.26
    çķĮ第ä¸Ģ
    -0.26
    çķĮ
    -0.25
    å·®çĤ¹
    -0.25
    [thread
    -0.25
     moo
    -0.25
    liced
    -0.25
    ä¸įçIJĨ
    -0.24
    éĻ©
    -0.24
    积æŀģæĢ§
    -0.24
    POSITIVE LOGITS
    ocht
    0.28
     rew
    0.27
    imen
    0.26
    _np
    0.26
     overcrow
    0.26
    epar
    0.26
     spelling
    0.26
    缸çĪ±
    0.24
    æĬķ
    0.24
     Iso
    0.24
    Activations Density 6.441%

    No Known Activations