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. 44000
    Prev
    Next
    INDEX
    Explanations

    spirituality and philosophy

    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
    然
    -0.07
    等多项
    -0.07
    �
    -0.06
    事が
    -0.06
     التطبيق
    -0.06
     propulsion
    -0.06
    くなって
    -0.06
     düzenlen
    -0.06
     creado
    -0.06
     surfing
    -0.06
    POSITIVE LOGITS
    INGER
    0.08
     Lean
    0.07
    erde
    0.07
     Bars
    0.07
    rai
    0.07
     Sciences
    0.07
     ARM
    0.07
    .bi
    0.07
    安静
    0.07
    Markers
    0.07
    Activations Density 0.086%

    No Known Activations