© 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. 88574
    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
    anner
    -0.35
    ANNER
    -0.32
    æŶåħī
    -0.31
    è¿ĩç¨ĭ
    -0.27
    èĴ½
    -0.27
     occurrences
    -0.25
    éļIJç§ģ
    -0.25
    OPY
    -0.24
     newspapers
    -0.24
     setTime
    -0.24
    POSITIVE LOGITS
    unt
    0.32
    iren
    0.27
    ries
    0.26
    饥
    0.25
     Reviewed
    0.25
    .IntPtr
    0.25
    æ·±åĪ»
    0.24
    untu
    0.24
    yleft
    0.24
    å¼¹
    0.24
    Activations Density 10.851%

    No Known Activations