© 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. 88510
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    illation
    -0.29
    å±Ī
    -0.28
    bfd
    -0.26
     augmentation
    -0.26
    éĻªä¼´
    -0.25
    å§ij
    -0.24
    assembly
    -0.24
    atro
    -0.24
    æĤ¯
    -0.24
    ENE
    -0.24
    POSITIVE LOGITS
    æµģè¡ĮçļĦ
    0.30
    arias
    0.28
     separate
    0.28
    esch
    0.26
    çļĦè§Ĵèī²
    0.26
     ROLE
    0.25
    并åıij
    0.24
    ont
    0.24
    æŀģæĺĵ
    0.24
     skips
    0.24
    Activations Density 17.919%

    No Known Activations