© 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. 32-TRANSCODER-HP
    7. 43614
    Prev
    Next
    INDEX
    Explanations

    Code and technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fall
    -0.29
     fall
    -0.28
    è°į
    -0.27
     fell
    -0.27
     falls
    -0.26
    ail
    -0.26
    èĢĥ
    -0.26
    è¯Ħè®®
    -0.26
    fall
    -0.25
    Fall
    -0.25
    POSITIVE LOGITS
     land
    0.52
    land
    0.45
     lands
    0.42
     Land
    0.42
    åľŁåľ°
    0.41
    lands
    0.40
    Land
    0.40
    éĻĨ
    0.38
    çļĦåľŁåľ°
    0.38
    _land
    0.37
    Activations Density 0.000%

    No Known Activations