© 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. 40169
    Prev
    Next
    INDEX
    Explanations

    s

    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
    éĺģ
    -0.34
    æ±Ĺ
    -0.30
    PerPage
    -0.26
    ä¸įæĸŃå¢ŀ强
    -0.24
    æļ´
    -0.24
    質
    -0.24
    vec
    -0.24
    饮
    -0.23
    èĻļ
    -0.23
    åĪĽ
    -0.23
    POSITIVE LOGITS
     prescribing
    0.30
    creasing
    0.26
    串èģĶ
    0.26
    reno
    0.26
     пом
    0.25
    CAPE
    0.25
    eam
    0.25
    iph
    0.25
     prescribe
    0.24
    eah
    0.24
    Activations Density 0.773%

    No Known Activations