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. 56404
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    不慎
    -0.08
    andon
    -0.07
     Sr
    -0.07
    HV
    -0.07
    _nth
    -0.07
    bw
    -0.07
     준
    -0.07
    障
    -0.07
     shines
    -0.07
    تل
    -0.07
    POSITIVE LOGITS
     classical
    0.08
    gorit
    0.08
    楩
    0.07
    ༼
    0.07
    pectral
    0.07
    镭
    0.07
     bastante
    0.07
    Palette
    0.07
    ﮧ
    0.07
    פשוט
    0.07
    Activations Density 0.005%

    No Known Activations