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. 11-RESID-POST-AA
    6. 1911
    Prev
    Next
    INDEX
    Explanations

    Spanish/Portuguese "enter"

    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
     autop
    -0.07
     findet
    -0.07
    ありが
    -0.07
     baptism
    -0.07
     mother
    -0.07
     médico
    -0.06
    쐐
    -0.06
    ather
    -0.06
     unbelie
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     لكل
    0.08
    .Char
    0.07
     Roc
    0.07
    ضرورة
    0.07
    充滿
    0.07
    芯
    0.07
    可以根据
    0.07
    享有
    0.07
     categorie
    0.07
    了一些
    0.07
    Activations Density 0.018%

    No Known Activations