© 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. 39162
    Prev
    Next
    INDEX
    Explanations

    1

    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
     ..."↵↵
    -0.44
    âĢ¦”↵↵
    -0.42
    ------↵↵
    -0.41
     —↵↵
    -0.41
    ...'↵
    -0.40
    -----↵↵
    -0.40
    ******↵↵
    -0.40
     ....↵↵
    -0.40
    *****↵↵
    -0.39
    ##↵↵
    -0.38
    POSITIVE LOGITS
    2
    0.35
    1
    0.34
    3
    0.31
    5
    0.31
    4
    0.31
    6
    0.29
    7
    0.28
    s
    0.27
    0
    0.27
    -loop
    0.27
    Activations Density 41.909%

    No Known Activations