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. 19-RESID-POST-AA
    6. 7264
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     delicious
    -0.08
     indemn
    -0.08
     WL
    -0.07
     denying
    -0.07
    .del
    -0.07
    _odd
    -0.07
     mail
    -0.07
     MQ
    -0.06
     plagiarism
    -0.06
    صاحب
    -0.06
    POSITIVE LOGITS
     위치
    0.07
     Som
    0.07
     Å
    0.07
     Seiten
    0.07
    工作机制
    0.07
    �
    0.07
    鬏
    0.07
     ?>:</
    0.07
    五行
    0.07
    ],[-
    0.06
    Activations Density 0.475%

    No Known Activations