© 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. 19-RESID-POST-AA
    6. 5457
    Prev
    Next
    INDEX
    Explanations

    the

    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
    常识
    -0.07
    Almost
    -0.07
    亮丽
    -0.07
     реально
    -0.06
    �
    -0.06
    售卖
    -0.06
     обычно
    -0.06
     @"\
    -0.06
     @"
    -0.06
    🥇
    -0.06
    POSITIVE LOGITS
     Columbus
    0.07
    ings
    0.07
     stainless
    0.07
    ournemouth
    0.07
     Turnbull
    0.07
    .what
    0.07
     Fires
    0.06
    锈
    0.06
     Kata
    0.06
    党风廉政
    0.06
    Activations Density 0.012%

    No Known Activations