© 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. 22722
    Prev
    Next
    INDEX
    Explanations

    Captured

    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
    aira
    -0.27
     Tester
    -0.26
    .support
    -0.25
     pinned
    -0.25
     invested
    -0.25
    rome
    -0.25
     depreci
    -0.25
    lest
    -0.25
    çĨ¨
    -0.25
     Sons
    -0.24
    POSITIVE LOGITS
    recover
    0.30
    Fs
    0.28
    arry
    0.28
    -ob
    0.28
    æ¡Ī件
    0.28
    管çIJĨåĬŀæ³ķ
    0.28
     Fs
    0.27
    seau
    0.27
    æľºåĪ¶
    0.27
    pose
    0.26
    Activations Density 0.000%

    No Known Activations