© 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. 7-RESID-POST-AA
    6. 76005
    Prev
    Next
    INDEX
    Explanations

    doInBackground

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    纷纷
    -0.07
    -ph
    -0.07
     Summon
    -0.07
    calc
    -0.07
    śnie
    -0.07
     infra
    -0.07
     scrub
    -0.07
    .sd
    -0.07
    잘
    -0.07
    地震
    -0.07
    POSITIVE LOGITS
    띌
    0.08
     StringType
    0.07
    {};↵
    0.07
    *dx
    0.07
    נחה
    0.07
    的目的
    0.07
    andReturn
    0.06
     ObjectType
    0.06
    Difference
    0.06
     RCC
    0.06
    Activations Density 0.001%

    No Known Activations