© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 123239
    Prev
    Next
    INDEX
    Explanations

    plug

    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
     добро
    -0.08
    ɩ
    -0.07
    rim
    -0.07
    M
    -0.07
    Items
    -0.07
     shelves
    -0.07
    崔
    -0.07
    Volume
    -0.07
    אד
    -0.07
     wm
    -0.07
    POSITIVE LOGITS
    �
    0.07
     OFF
    0.07
     OR
    0.07
    렬
    0.07
    .transport
    0.07
    (par
    0.07
    .partial
    0.06
    纂
    0.06
     discharged
    0.06
     &);↵
    0.06
    Activations Density 0.006%

    No Known Activations