Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 48415
    Prev
    Next
    INDEX
    Explanations

    rest

    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
    뵜
    -0.07
     UIB
    -0.07
    環境
    -0.06
    🗺
    -0.06
    technology
    -0.06
     poster
    -0.06
    Individual
    -0.06
    GX
    -0.06
    hv
    -0.06
     improv
    -0.06
    POSITIVE LOGITS
     Florida
    0.08
    Fall
    0.07
    ­i
    0.07
     inode
    0.07
     propagated
    0.07
     Brennan
    0.07
     Works
    0.07
     وبالتالي
    0.07
     Wal
    0.07
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    0.07
    Activations Density 0.024%

    No Known Activations