© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24870
    Prev
    Next
    INDEX
    Explanations

    quotation marks, parentheses

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Attendance
    -0.07
     conflic
    -0.07
    Bit
    -0.07
    XP
    -0.06
    所需
    -0.06
     tonumber
    -0.06
    苔
    -0.06
    (((
    -0.06
     oxidative
    -0.06
     frequent
    -0.06
    POSITIVE LOGITS
    ߞ
    0.08
    姚明
    0.07
    婼
    0.07
     interventions
    0.07
    pcm
    0.07
    𝙡
    0.07
     Joker
    0.07
    iqué
    0.07
    encv
    0.07
     essay
    0.06
    Activations Density 0.008%

    No Known Activations