© 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. 23679
    Prev
    Next
    INDEX
    Explanations

    game

    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
     Kem
    -0.26
    quets
    -0.25
    arro
    -0.25
    ESIS
    -0.25
    æĹ¥çĶµ
    -0.25
    è®®é¢ĺ
    -0.25
    èĦijæµ·ä¸Ń
    -0.24
    amient
    -0.24
    ç»´å°Ķ
    -0.24
     '~/
    -0.23
    POSITIVE LOGITS
    umas
    0.28
    riad
    0.28
    á»ijn
    0.27
     vehicles
    0.24
    å¾¼
    0.24
     scientific
    0.24
    mak
    0.24
     figure
    0.24
    \Model
    0.24
    ¥
    0.24
    Activations Density 0.001%

    No Known Activations