© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 74720
    Prev
    Next
    INDEX
    Explanations

    Programming code/definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    csrf
    -0.07
     đáo
    -0.07
    智
    -0.06
     auth
    -0.06
     cd
    -0.06
    胗
    -0.06
     setLoading
    -0.06
     restless
    -0.06
    .Test
    -0.06
    nodoc
    -0.06
    POSITIVE LOGITS
    ferred
    0.09
    érer
    0.08
    有限公司
    0.07
    化的
    0.07
     theor
    0.07
    给他们
    0.07
    可在
    0.07
     האמר
    0.07
    日本
    0.07
     Há
    0.07
    Activations Density 0.024%

    No Known Activations