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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 39824
    Prev
    Next
    INDEX
    Explanations

    apostrophe, quotation mark

    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
     Virus
    -0.07
    㳇
    -0.07
    的孩子
    -0.07
    人民日报
    -0.07
    墙体
    -0.07
     Du
    -0.07
    ふ
    -0.07
    ירוע
    -0.06
     estud
    -0.06
     rare
    -0.06
    POSITIVE LOGITS
     vezes
    0.07
    限
    0.07
    moves
    0.07
     hours
    0.07
    emergency
    0.07
     centre
    0.07
     HOUR
    0.07
    buster
    0.07
    lose
    0.07
    qc
    0.07
    Activations Density 0.003%

    No Known Activations