© 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. 11-RESID-POST-AA
    6. 25388
    Prev
    Next
    INDEX
    Explanations

    privacy

    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
    Packet
    -0.08
    (extension
    -0.07
    von
    -0.07
     Generator
    -0.07
     payment
    -0.07
    设计方案
    -0.07
    Br
    -0.07
    vehicle
    -0.06
    dealer
    -0.06
    .",
    ↵
    -0.06
    POSITIVE LOGITS
    햊
    0.07
     CP
    0.07
    (choices
    0.07
    _difference
    0.07
    .tables
    0.06
    樱桃
    0.06
     требова
    0.06
     ObjectType
    0.06
     שכל
    0.06
    ﻡ
    0.06
    Activations Density 0.045%

    No Known Activations