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. 71885
    Prev
    Next
    INDEX
    Explanations

    Figures of speech

    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
     Etsy
    -0.07
    vero
    -0.07
     Morr
    -0.07
    orest
    -0.07
    	cerr
    -0.07
    cılar
    -0.07
    打压
    -0.07
     Birch
    -0.07
    kept
    -0.07
    뽀
    -0.07
    POSITIVE LOGITS
     prod
    0.07
     obey
    0.07
    commands
    0.07
    鲾
    0.06
     warnings
    0.06
    média
    0.06
    limit
    0.06
    xies
    0.06
     вид
    0.06
    waves
    0.06
    Activations Density 0.019%

    No Known Activations