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. 14003
    Prev
    Next
    INDEX
    Explanations

    acet

    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
    quent
    -0.08
    נן
    -0.07
    InBackground
    -0.07
    (tf
    -0.07
     Musk
    -0.07
    intendent
    -0.07
     inflater
    -0.07
    exual
    -0.06
     Fitzgerald
    -0.06
     già
    -0.06
    POSITIVE LOGITS
    ;amp
    0.07
     polys
    0.07
     demands
    0.07
    䔀
    0.07
    🏹
    0.07
    �
    0.06
    _qp
    0.06
     /////
    0.06
    شعب
    0.06
     ricerca
    0.06
    Activations Density 0.003%

    No Known Activations