© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7501
    Prev
    Next
    INDEX
    Explanations

    Formal statements and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¸Ħà¸ĩ
    -0.27
    对éĿ¢
    -0.25
     guarding
    -0.25
    dot
    -0.24
    çķ¥
    -0.24
    abal
    -0.23
    venues
    -0.23
     fitting
    -0.23
    eb
    -0.23
    ociety
    -0.23
    POSITIVE LOGITS
    icide
    0.27
    æķĹ
    0.25
    isle
    0.25
    TRY
    0.25
    带头人
    0.25
    trys
    0.24
    éĶ¶
    0.24
    fsp
    0.24
    ratio
    0.24
    imity
    0.24
    Activations Density 0.046%

    No Known Activations