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. 2336
    Prev
    Next
    INDEX
    Explanations

    code with length property

    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
    .xaxis
    -0.07
    closest
    -0.07
    ⚓
    -0.07
    �
    -0.06
    䃅
    -0.06
    iores
    -0.06
    	finally
    -0.06
    .JsonIgnore
    -0.06
    .masksToBounds
    -0.06
    Taylor
    -0.06
    POSITIVE LOGITS
    ODO
    0.07
     prohibit
    0.07
    .",
    ↵
    0.07
    不见
    0.07
     Guarantee
    0.07
     Speak
    0.07
    URY
    0.07
    ム
    0.07
     Regulation
    0.06
    حصول
    0.06
    Activations Density 0.005%

    No Known Activations