Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 127959
    Prev
    Next
    INDEX
    Explanations

    Eucharist/Catholicism

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .mvp
    -0.08
    ਊ
    -0.08
    <App
    -0.07
    主教练
    -0.07
     cổ
    -0.07
     hamm
    -0.07
    名字
    -0.07
     grade
    -0.07
    -grade
    -0.07
    עצמאי
    -0.06
    POSITIVE LOGITS
     mafia
    0.08
     Deus
    0.07
     Pokemon
    0.07
     Hunters
    0.07
     Shotgun
    0.07
     dentro
    0.07
     Kyoto
    0.07
     Knock
    0.07
     synopsis
    0.07
    פוליט
    0.06
    Activations Density 0.004%

    No Known Activations