Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 115333
    Prev
    Next
    INDEX
    Explanations

    starting

    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
    权利
    -0.07
     использование
    -0.07
    .parentNode
    -0.07
    _<?
    -0.07
    .ham
    -0.07
     ADS
    -0.07
    (Route
    -0.07
    (simp
    -0.06
    ıld
    -0.06
     movable
    -0.06
    POSITIVE LOGITS
    ce
    0.07
     o
    0.07
    according
    0.07
     công
    0.07
     unreachable
    0.07
     detailing
    0.07
    Managed
    0.06
    amientos
    0.06
    *);↵
    0.06
    Scores
    0.06
    Activations Density 0.028%

    No Known Activations