© 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. 88622
    Prev
    Next
    INDEX
    Explanations

    the

    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
    æĦŁè§¦
    -0.28
    ohon
    -0.26
    emap
    -0.25
     stap
    -0.24
     particul
    -0.23
    å°ıæŶåīį
    -0.23
    å§ijå¨ĺ
    -0.23
    æİĮ
    -0.23
     yaÅŁan
    -0.23
    пиÑģÑĮ
    -0.23
    POSITIVE LOGITS
    atement
    0.26
    -scenes
    0.26
     ent
    0.25
     ),
    0.25
    æ¸Ĭ
    0.25
     fi
    0.25
    åıŁ
    0.24
    umes
    0.24
    çĸıéĢļ
    0.24
     tracks
    0.24
    Activations Density 5.877%

    No Known Activations