Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 48658
    Prev
    Next
    INDEX
    Explanations

    is

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Publish
    -0.07
    韬
    -0.07
    ⋮
    -0.06
    在于
    -0.06
    忳
    -0.06
    Tar
    -0.06
     tavern
    -0.06
     MEM
    -0.06
    tout
    -0.06
     storytelling
    -0.06
    POSITIVE LOGITS
    don
    0.07
     ['.
    0.07
     数据
    0.07
    心目
    0.07
    告诉他
    0.07
     convenience
    0.06
    几百
    0.06
    нос
    0.06
    LEASE
    0.06
     ха
    0.06
    Activations Density 0.028%

    No Known Activations