© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 28483
    Prev
    Next
    INDEX
    Explanations

    of

    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
    _ioctl
    -0.08
    primitive
    -0.07
    .dom
    -0.07
     actionable
    -0.07
    轺
    -0.07
     isValid
    -0.07
    -send
    -0.07
    Tpl
    -0.07
    @Web
    -0.07
    ຈ
    -0.07
    POSITIVE LOGITS
    اعة
    0.08
     자리
    0.07
     cart
    0.07
    إبد
    0.07
    كان
    0.07
     Sector
    0.07
    -mort
    0.07
    azi
    0.07
    KANJI
    0.07
    煙
    0.06
    Activations Density 0.041%

    No Known Activations