© 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. 35-TRANSCODER-HP
    7. 39874
    Prev
    Next
    INDEX
    Explanations

    d

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įçĦ¶
    -0.25
    fram
    -0.24
    åħ¶å®ŀ
    -0.24
     Hoe
    -0.24
    pane
    -0.24
    га
    -0.24
    æķĪèĥ½
    -0.24
    furt
    -0.23
    TEE
    -0.23
     motive
    -0.23
    POSITIVE LOGITS
    uent
    0.27
    éĥ¨èIJ½
    0.25
    ec
    0.24
    æ°ı
    0.23
    åĩŃçĿĢ
    0.23
     cant
    0.23
    eca
    0.23
    idle
    0.23
    RITE
    0.23
     rough
    0.23
    Activations Density 62.091%

    No Known Activations