© 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. 40215
    Prev
    Next
    INDEX
    Explanations

    code

    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
    æĬĵ好
    -0.22
     Rock
    -0.22
     flame
    -0.21
    建档
    -0.21
    æĬĵ
    -0.21
    ·¸
    -0.20
    åİ¢
    -0.20
    骨骼
    -0.20
     Jail
    -0.20
    enance
    -0.20
    POSITIVE LOGITS
    r
    1.33
    rn
    0.93
    rq
    0.91
    rk
    0.91
    rad
    0.88
    rig
    0.87
    ras
    0.86
    rin
    0.86
    rh
    0.85
    ran
    0.85
    Activations Density 88.978%

    No Known Activations