© 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. 108291
    Prev
    Next
    INDEX
    Explanations

    be

    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
    ees
    -0.28
    cks
    -0.25
    atel
    -0.25
     inne
    -0.25
    tlement
    -0.25
     copyrights
    -0.24
     Lionel
    -0.23
     bare
    -0.23
    æĥ°
    -0.23
     copyright
    -0.23
    POSITIVE LOGITS
    åĬŀ
    0.27
     handleChange
    0.27
    @$
    0.27
    æ¶Īæģ¯
    0.26
    çĿ£åĬŀ
    0.26
    åĬŀ好
    0.26
    çļĦæ¶Īæģ¯
    0.26
    èĽĭ
    0.26
    chg
    0.25
    eny
    0.25
    Activations Density 0.889%

    No Known Activations