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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23-RESID-POST-AA
    6. 728
    Prev
    Next
    INDEX
    Explanations

    lo

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ();
    -0.07
    rouch
    -0.07
    .ev
    -0.07
    italic
    -0.07
    Choose
    -0.07
    vertex
    -0.07
    留言板
    -0.07
    .TimeUnit
    -0.06
     rotate
    -0.06
    >(),↵
    -0.06
    POSITIVE LOGITS
     limitation
    0.07
     Installation
    0.07
    把她
    0.07
    connecting
    0.07
     bombing
    0.07
     serviço
    0.06
     장
    0.06
     воздейств
    0.06
     ремонт
    0.06
    \Resources
    0.06
    Activations Density 0.020%

    No Known Activations