© 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. 53801
    Prev
    Next
    INDEX
    Explanations

    ple

    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
     dom
    -0.26
    æ´»
    -0.26
     dome
    -0.25
    ouver
    -0.25
    eny
    -0.24
    atorial
    -0.24
    èĭŁ
    -0.24
    grim
    -0.24
    xbb
    -0.24
    IPH
    -0.24
    POSITIVE LOGITS
    capt
    0.29
    ìĽĶ
    0.26
    æĦŁ
    0.26
    ëĤ©
    0.26
    stantiate
    0.26
    unu
    0.26
     estava
    0.25
    :id
    0.25
    æįķæįī
    0.25
    æįķ
    0.25
    Activations Density 0.002%

    No Known Activations