© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 1905
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     année
    -0.09
     are
    -0.08
    idis
    -0.08
    �
    -0.08
    (ele
    -0.07
    (pos
    -0.07
    'a
    -0.07
    fas
    -0.07
    uxt
    -0.07
    来说
    -0.07
    POSITIVE LOGITS
    translations
    0.08
    受理
    0.07
    歹
    0.07
    TextWriter
    0.07
    流氓
    0.07
    矿泉水
    0.07
    Americ
    0.07
     drinking
    0.07
    哐
    0.07
     tờ
    0.07
    Activations Density 0.014%

    No Known Activations