© 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. 88647
    Prev
    Next
    INDEX
    Explanations

    history

    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
    æŶéĹ´æ®µ
    -0.30
    æķ£
    -0.28
    ungen
    -0.25
    åħ·ä½ĵçļĦ
    -0.25
    egen
    -0.25
    åĬŀçIJĨ
    -0.24
     bulk
    -0.24
    çĸ«æĥħæľŁéĹ´
    -0.24
    åħ¸åŀĭçļĦ
    -0.24
    çŃīå¥ĸ
    -0.24
    POSITIVE LOGITS
    alah
    0.30
    åĨ³çŃĸ
    0.27
     discriminate
    0.25
    [ix
    0.25
    retval
    0.25
    xFE
    0.25
    åĶĩ
    0.24
     диÑĢ
    0.24
    *****↵↵
    0.24
    æĸ°æĶ¿
    0.24
    Activations Density 11.552%

    No Known Activations