© 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. 12-TRANSCODER-HP
    7. 23567
    Prev
    Next
    INDEX
    Explanations

    &#

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    身ä¸Ĭ
    -0.29
    éĩĩ
    -0.26
     contacts
    -0.26
    çļĦåı¯èĥ½æĢ§
    -0.25
    æĸĻ
    -0.25
    amination
    -0.25
    usal
    -0.25
     princip
    -0.25
     Princip
    -0.25
    éļ¾åº¦
    -0.24
    POSITIVE LOGITS
    ’Brien
    0.32
    ĵį
    0.28
    ä½į
    0.27
    agedList
    0.26
     Lug
    0.25
    aday
    0.24
     cheated
    0.24
    çĶ¨æĪ·æıIJä¾Ľ
    0.24
    zburg
    0.24
    æ¶Īè´¹åįĩ级
    0.24
    Activations Density 0.000%

    No Known Activations