© 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. 107398
    Prev
    Next
    INDEX
    Explanations

    2

    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
    -0.15
    å±ķ
    -0.14
    å°ij
    -0.14
    2
    -0.13
    .
    -0.13
     effects
    -0.13
    1
    -0.13
    4
    -0.13
    “
    -0.13
     embedding
    -0.13
    POSITIVE LOGITS
    æĿľåħ°
    0.14
    OMPI
    0.13
    åī§ä¸Ń
    0.13
    territ
    0.13
    ospel
    0.12
    —if
    0.12
    ,'#
    0.12
     geopol
    0.12
    NSObject
    0.12
     disarm
    0.12
    Activations Density 1.497%

    No Known Activations