© 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
    2. Qwen3-4B
    3. 25-TRANSCODER-HP
    4. 108397
    Prev
    Next
    INDEX
    Explanations

    and

    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
    ύ
    -0.31
    anches
    -0.27
    alité
    -0.27
    èħ¹
    -0.27
    æªĶ
    -0.26
    -Sep
    -0.26
    anche
    -0.26
    gid
    -0.25
    åºĬä¸Ĭ
    -0.25
    ério
    -0.25
    POSITIVE LOGITS
     Cover
    0.28
    ↵↵↵↵
    0.27
    &
    0.27
     &
    0.27
     Hint
    0.26
     Done
    0.26
     
    0.26
    ?
    0.26
     Illustr
    0.25
     while
    0.25
    Activations Density 0.892%

    No Known Activations