© 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. 25-TRANSCODER-HP
    7. 108369
    Prev
    Next
    INDEX
    Explanations

    Jew

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iphy
    -0.28
    uParam
    -0.28
    uÅŁ
    -0.25
    å¹¿æ³Ľ
    -0.25
    uC
    -0.24
     earners
    -0.24
     #č↵
    -0.24
    neutral
    -0.24
    ybrid
    -0.24
    usher
    -0.23
    POSITIVE LOGITS
    tics
    0.26
     Hammer
    0.26
     floor
    0.26
     sling
    0.25
    oly
    0.25
    oor
    0.24
    åı¯ä»¥è¯´
    0.24
    éĺķ
    0.24
     inherent
    0.24
    à¹ĩà¸Ķ
    0.24
    Activations Density 0.919%

    No Known Activations