© 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. 108055
    Prev
    Next
    INDEX
    Explanations

    technical processes involving material

    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
    ogie
    -0.27
    è¶Ĭ
    -0.25
    DIG
    -0.25
     голоÑģ
    -0.25
     kid
    -0.24
    pac
    -0.24
    åĨħãģ§
    -0.24
    ictions
    -0.24
     PAC
    -0.24
     Kid
    -0.23
    POSITIVE LOGITS
    iran
    0.33
    äºĶéĩij
    0.32
     elasticity
    0.27
     hides
    0.27
    arta
    0.26
     Blvd
    0.25
    æ¦Ķ
    0.25
    alten
    0.25
    inos
    0.25
    flux
    0.25
    Activations Density 0.083%

    No Known Activations