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. 19-RESID-POST-AA
    6. 2220
    Prev
    Next
    INDEX
    Explanations

    was

    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
    近乎
    -0.08
    私人
    -0.08
    偓
    -0.08
    atra
    -0.07
    tog
    -0.07
    bcm
    -0.07
     brit
    -0.07
    ={"/
    -0.07
    dit
    -0.07
    Ѷ
    -0.07
    POSITIVE LOGITS
    concat
    0.07
    Root
    0.07
     algorithm
    0.07
    _Sh
    0.06
    Rad
    0.06
    サイト
    0.06
    Akt
    0.06
     서비스
    0.06
    walker
    0.06
    ergarten
    0.06
    Activations Density 0.009%

    No Known Activations