© 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. 141497
    Prev
    Next
    INDEX
    Explanations

    state

    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
    eren
    -0.30
    joint
    -0.27
    licht
    -0.27
    æī¼
    -0.27
    egr
    -0.26
    zer
    -0.25
    æķ¦
    -0.24
    lick
    -0.24
    lic
    -0.24
     courtesy
    -0.24
    POSITIVE LOGITS
    èĩ¾
    0.25
    (amount
    0.24
    leccion
    0.24
    篾
    0.24
    éĿĴå±±
    0.24
    ëĦ·
    0.24
    æ¸ħé¦Ļ
    0.24
     offs
    0.24
    æĶ¾ä¸ĭ
    0.24
    rawn
    0.24
    Activations Density 0.778%

    No Known Activations