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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 121254
    Prev
    Next
    INDEX
    Explanations

    Plunker URLs

    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
    -padding
    -0.08
     mover
    -0.07
    нибуд
    -0.07
    (INVOKE
    -0.07
    lexical
    -0.07
    �新
    -0.07
    (job
    -0.07
    モデ
    -0.06
    確
    -0.06
    =edge
    -0.06
    POSITIVE LOGITS
    _hit
    0.07
    ")));↵
    0.07
     המשפחה
    0.07
    专辑
    0.06
    �
    0.06
    Source
    0.06
    瑬
    0.06
     Ön
    0.06
    _dir
    0.06
     dell
    0.06
    Activations Density 0.002%

    No Known Activations