© 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. 20-TRANSCODER-HP
    7. 130627
    Prev
    Next
    INDEX
    Explanations

    Prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CB
    -0.28
    _ok
    -0.26
    .ent
    -0.25
    _cb
    -0.25
    _ent
    -0.25
     Favor
    -0.25
    ustin
    -0.25
     Curtain
    -0.24
     Ack
    -0.24
    çıį
    -0.24
    POSITIVE LOGITS
    ibre
    0.27
    ç²Ĺ
    0.27
    corp
    0.26
     cocks
    0.26
    女æİĴ
    0.25
    BuilderInterface
    0.25
    å¼ĢåIJ¯äºĨ
    0.25
    豨
    0.24
    åı¯ä»¥å¸®åĬ©
    0.24
    åı¦æľī
    0.24
    Activations Density 16.423%

    No Known Activations