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. 25103
    Prev
    Next
    INDEX
    Explanations

    permitted

    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
    _CheckedChanged
    -0.07
    lige
    -0.07
     mijn
    -0.07
    	volatile
    -0.07
     il
    -0.07
     ترك
    -0.07
    ﻞ
    -0.07
    ós
    -0.07
    保鲜
    -0.07
     heightFor
    -0.06
    POSITIVE LOGITS
     baker
    0.08
    شاب
    0.07
    ряд
    0.07
     troll
    0.07
    _question
    0.07
     nhiễm
    0.07
     bystand
    0.07
     QByteArray
    0.07
    mutation
    0.07
    נזק
    0.07
    Activations Density 0.008%

    No Known Activations