© 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. 22947
    Prev
    Next
    INDEX
    Explanations

    licenses and legal disclaimers

    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
     advis
    -0.26
    entrant
    -0.26
    aviour
    -0.26
     overshadow
    -0.25
     accommodating
    -0.24
    LOAT
    -0.24
    clearfix
    -0.24
    enticator
    -0.23
     overwhelmed
    -0.23
    æ½®æµģ
    -0.23
    POSITIVE LOGITS
    åįıä¼ļä¼ļåijĺ
    0.30
    meer
    0.27
     Plains
    0.26
    ëķħ
    0.26
    çĶĺ
    0.26
    åĵģè´¨
    0.26
    æĬĬæīĭ
    0.26
    als
    0.25
    ties
    0.25
     Assoc
    0.25
    Activations Density 0.010%

    No Known Activations