© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 704
    Prev
    Next
    INDEX
    Explanations

    Maryland legal cases

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     infrared
    -0.07
     ARM
    -0.07
    _BOOL
    -0.06
    战场上
    -0.06
    announce
    -0.06
    Desk
    -0.06
     универ
    -0.06
    orb
    -0.06
    lightbox
    -0.06
    Fran
    -0.06
    POSITIVE LOGITS
    (entries
    0.08
    _SIMPLE
    0.07
     frei
    0.07
    ╍
    0.07
    ISIBLE
    0.07
    消费者
    0.07
     pi
    0.07
     Laboratories
    0.07
    憙
    0.07
     pari
    0.07
    Activations Density 0.120%

    No Known Activations