© 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. 19-TRANSCODER-HP
    7. 8418
    Prev
    Next
    INDEX
    Explanations

    scientific publications

    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
    лÑıÑĢ
    -0.30
    éľĸ
    -0.27
    :^
    -0.25
    :_
    -0.24
     EAST
    -0.23
    erval
    -0.23
     details
    -0.23
    xad
    -0.23
    lia
    -0.23
    :]
    -0.23
    POSITIVE LOGITS
    .choices
    0.29
    èĪ¸
    0.29
    å°±ä¸įä¼ļ
    0.27
    è¶ĭ
    0.26
    åı¯è§ĨåĮĸ
    0.25
    ariat
    0.25
    erre
    0.24
    å§Ĭ妹
    0.24
    åįıåIJĮåıijå±ķ
    0.24
    choices
    0.24
    Activations Density 0.014%

    No Known Activations