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. 36120
    Prev
    Next
    INDEX
    Explanations

    generator

    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
     '</
    -0.08
    dcc
    -0.07
     RVA
    -0.07
     Feel
    -0.07
    滨江
    -0.07
    -urlencoded
    -0.07
    触
    -0.07
    fare
    -0.07
     Insight
    -0.07
     Portrait
    -0.07
    POSITIVE LOGITS
    Generator
    0.07
    OR
    0.07
    иров
    0.06
     obtener
    0.06
    引
    0.06
    散
    0.06
     forever
    0.06
     Img
    0.06
     größ
    0.06
     generator
    0.06
    Activations Density 0.004%

    No Known Activations