© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 76077
    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
     дер
    -0.08
    _samples
    -0.08
    �
    -0.07
    谷爱
    -0.07
     itk
    -0.07
    'im
    -0.07
     Ivy
    -0.07
    感染者
    -0.07
     impulse
    -0.06
    .si
    -0.06
    POSITIVE LOGITS
     Finally
    0.07
     Alan
    0.07
    봉
    0.07
    orph
    0.07
     heroine
    0.07
     ano
    0.07
    团队
    0.07
    ulary
    0.06
     broaden
    0.06
    وفق
    0.06
    Activations Density 0.001%

    No Known Activations