© 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. 24-TRANSCODER-HP
    7. 149959
    Prev
    Next
    INDEX
    Explanations

    goals, targets, objectives

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     buffet
    -0.31
    isque
    -0.27
    è¿©
    -0.27
    achable
    -0.26
    assis
    -0.26
    -origin
    -0.25
     Bowen
    -0.25
    ean
    -0.25
    erus
    -0.25
     enormous
    -0.24
    POSITIVE LOGITS
    acy
    0.34
    ACY
    0.28
    éĵ¾æİ¥
    0.28
    ÐļÐŀ
    0.25
     Patri
    0.25
     sexuality
    0.25
    agedList
    0.25
     partner
    0.25
    çĤĬ
    0.24
    co
    0.24
    Activations Density 0.120%

    No Known Activations