© 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. 33-TRANSCODER-HP
    7. 52994
    Prev
    Next
    INDEX
    Explanations

    locations and areas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ricks
    -0.28
    chains
    -0.28
    å§IJ妹
    -0.27
    żu
    -0.27
    buquerque
    -0.26
     Posts
    -0.26
    æł¡åĮº
    -0.25
    coins
    -0.25
    etsk
    -0.25
    lös
    -0.25
    POSITIVE LOGITS
    çĪµå£«
    0.28
    ISC
    0.28
    anc
    0.27
    oure
    0.26
    ento
    0.26
     Curve
    0.26
    è·¯è¿ĩ
    0.26
     ara
    0.26
     pull
    0.25
     lot
    0.25
    Activations Density 0.014%

    No Known Activations