© 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. 88891
    Prev
    Next
    INDEX
    Explanations

    documentation, code, question/answer

    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
    个å¤ļ
    -0.28
    ikipedia
    -0.27
    éľĸ
    -0.26
     NOI
    -0.25
    accum
    -0.24
    å¹ħ度
    -0.24
    æĥħåĨµä¸ĭ
    -0.24
     risen
    -0.24
    etta
    -0.24
    foot
    -0.23
    POSITIVE LOGITS
    ATORY
    0.30
    зи
    0.26
    éĺĸ
    0.26
    æĶ¶è´¹æłĩåĩĨ
    0.25
    ison
    0.24
    æ£Ħ
    0.24
    prech
    0.24
     Sized
    0.24
    åºľ
    0.24
    è´´
    0.24
    Activations Density 15.598%

    No Known Activations