© 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. 89530
    Prev
    Next
    INDEX
    Explanations

    Common words and 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
    _VM
    -0.28
    BAR
    -0.28
     Came
    -0.27
    åģļ人
    -0.27
    åĬŀäºĭ
    -0.27
    bill
    -0.26
    常è§ģ
    -0.26
    èĦī
    -0.25
    ++↵↵
    -0.25
    è£ģåĪ¤
    -0.25
    POSITIVE LOGITS
    产éĶĢ
    0.28
    anel
    0.25
    -LAST
    0.24
    ancell
    0.24
    ulpt
    0.24
    marvin
    0.24
     primitive
    0.23
     situation
    0.23
    _MATH
    0.23
    },{"
    0.23
    Activations Density 3.134%

    No Known Activations