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. 7217
    Prev
    Next
    INDEX
    Explanations

    null and non-null

    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
    Px
    -0.08
    𝑼
    -0.07
    樱桃
    -0.07
     JL
    -0.07
     MPL
    -0.07
    меди
    -0.07
    🔢
    -0.07
    ])(
    -0.07
     Emil
    -0.07
    _pixels
    -0.07
    POSITIVE LOGITS
    廊坊
    0.07
    orough
    0.07
    laş
    0.07
    	getline
    0.07
    (&(
    0.06
    一如既
    0.06
    奇特
    0.06
    .signature
    0.06
     ensures
    0.06
     Leia
    0.06
    Activations Density 0.001%

    No Known Activations