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. 72445
    Prev
    Next
    INDEX
    Explanations

    Text excerpts

    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
    的能量
    -0.08
    Mismatch
    -0.07
     altru
    -0.07
     aberr
    -0.07
    蟆
    -0.07
    是多么
    -0.07
    违反
    -0.07
     accidents
    -0.06
    被淘汰
    -0.06
    :list
    -0.06
    POSITIVE LOGITS
     explic
    0.07
    _Edit
    0.07
    죌
    0.07
     HBO
    0.07
    โอก
    0.07
     exclus
    0.07
     es
    0.07
     específ
    0.07
    илась
    0.07
    _OPT
    0.07
    Activations Density 0.025%

    No Known Activations