© 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. 33-TRANSCODER-HP
    7. 53525
    Prev
    Next
    INDEX
    Explanations

    ot

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    强åĪ¶
    -0.27
     rib
    -0.27
    abin
    -0.27
    úc
    -0.26
    rid
    -0.26
    éĶ¡
    -0.25
    ä¸Ģå®ļèĥ½
    -0.25
    ichi
    -0.25
     pdo
    -0.25
    paginator
    -0.24
    POSITIVE LOGITS
     George
    0.29
    onium
    0.27
    滩
    0.27
    George
    0.25
    漪
    0.24
    说äºĨ
    0.24
    æ¦ľ
    0.24
    strate
    0.23
    PathVariable
    0.23
    èĴ
    0.23
    Activations Density 0.005%

    No Known Activations