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. 127868
    Prev
    Next
    INDEX
    Explanations

    are

    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
    庠
    -0.08
    atitude
    -0.07
     realtime
    -0.07
    _UID
    -0.07
    奘
    -0.07
    回首
    -0.07
     chẳng
    -0.06
     unfolds
    -0.06
    موت
    -0.06
    まと
    -0.06
    POSITIVE LOGITS
    脾气
    0.07
    Grey
    0.07
     working
    0.07
    _detector
    0.06
    _house
    0.06
     Fab
    0.06
    앰
    0.06
    -index
    0.06
     skills
    0.06
    WebElement
    0.06
    Activations Density 0.006%

    No Known Activations